ICASSP 2008 - PDF Preprint Papers

ICASSP 2008 Speech Acoustics

Teaser Browsing | Click Here

Title Browsing | Click Here

Wall of Fame | Most Viewed ICASSP-2008 Paper

click to vote

ICASSP
2008
IEEE

331views Signal Processing» more ICASSP 2008»

Unsupervised optimal phoneme segmentation: Objectives, algorithm and comparisons

14 years 5 months ago

Download www.gavo.t.u-tokyo.ac.jp

Phoneme segmentation is a fundamental problem in many speech recognition and synthesis studies. Unsupervised phoneme segmentation assumes no knowledge on linguistic contents and a...

Yu Qiao, Naoya Shimomura, Nobuaki Minematsu

claim paper

Read More »

Disclaimer and Copyright Notice

Sciweavers respects the rights of all copyright holders and in this regard, authors are only allowed to share a link to their preprint paper on their own website. Every contribution is associated with a desciptive image. It is the sole responsibility of the authors to ensure that their posted image is not copyright infringing. This service is compliant with IEEE copyright.

Id	Views	Title	Status

1	331	Unsupervised optimal phoneme segmentation: Objectives, algorithm and comparisons	claim
2	300	3D facial expression recognition using swarm intelligence	claim
3	293	Dynamic signature verification with template protection using helper data	claim
4	286	Query adaptative locality sensitive hashing	claim
5	281	Parametric estimation of affine deformations of binary images
6	263	2D to 3D convertion based on edge defocus and segmentation	claim
7	247	Algebraic visual cryptography scheme for color images	claim
8	246	Generalized Gaussian Markov random field image restoration using variational distribution approximation	claim
9	240	Power control in spectrum overlay networks: How to cross a multi-lane highway	claim
10	234	A hierarchical point process model for speech recognition	claim
11	233	Compressive sensing and waveform design for the identification of Linear time-varying systems	claim
12	230	Performance characteristics of collaborative beamforming for wireless sensor networks with Gaussian distributed sensor nodes	claim
13	228	View invariant gesture recognition using 3D motion primitives	claim
14	227	Blind separation of non-negative sources by convex analysis: Effective method using linear programming	claim
15	222	A two-stage approach to saliency detection in images	claim
16	221	Unsupervised language model adaptation via topic modeling based on named entity hypotheses	claim
17	218	Mutual information based relevance network analysis: a Parkinson'S disease study	claim
18	218	Optimal stochastic dual resource allocation for cognitive radios based on quantized CSI	claim
19	217	Discriminative feature selection for hidden Markov models using Segmental Boosting	claim
20	217	Compensation of RF impairments in MIMO OFDM systems	claim
21	216	Nested support vector machines	claim
22	215	Multimodal information fusion using the iterative decoding algorithm and its application to audio-visual speech recognition	claim
23	215	Bayesian update of dialogue state for robust dialogue systems	claim
24	214	Hybrid feature selection for gesture recognition using support vector machines	claim
25	214	Audiovisual-to-articulatory speech inversion using Active Appearance Models for the face and Hidden Markov Models for the dynamics	claim
26	214	OFDM for underwater acoustic communications: Adaptive synchronization and sparse channel estimation	claim
27	208	Transmit codes and receive filters for pulse compression radar systems	claim
28	207	Image inpainting with a wavelet domain Hidden Markov tree model	claim
29	207	Singer melody extraction in polyphonic signals using source separation methods	claim
30	207	Simultaneous and fast 3D tracking of multiple faces in video by GPU-based stream processing	claim
31	206	Mixed-signal parallel compressed sensing and reception for cognitive radio	claim
32	204	Maximum entropy relaxation for multiscale graphical model selection	claim
33	204	Efficient soft demodulation of MIMO QPSK via semidefinite relaxation	claim
34	203	Perceptually weighted distortion measures and the tandem connection of speech codecs	claim
35	201	A normalized adaptation scheme for the convex combination of two adaptive filters	claim
36	200	A new mutual information measure for independent component alalysis	claim
37	200	Iteratively reweighted algorithms for compressive sensing	claim
38	197	Wavelet-domain compressive signal reconstruction using a Hidden Markov Tree model	claim
39	196	Action recognition using spatio-temporal regularity based features	claim
40	196	A compressive beamforming method	claim
41	194	Stereo matching with asymmetric occlusion handling in weighted least square framework	claim
42	192	Remeshing and spatio-temporal wavelet filtering for 3D animations	claim
43	192	Camera and microphone array for 3D audiovisual face data collection	claim
44	192	Separation of overlapping RFID signals by antenna arrays	claim
45	191	Abnormal event detection based on trajectory clustering by 2-depth greedy search	claim
46	191	Using corpus and knowledge-based similarity measure in Maximum Marginal Relevance for meeting summarization	claim
47	190	Automatic Flamingo detection using a multiple birth and death process	claim
48	190	Permutation grouping: intelligent Hash function design for audio & image retrieval	claim
49	190	Quick fmllr for speaker adaptation in speech recognition	claim
50	185	Insights into the stable recovery of sparse solutions in overcomplete representations using network information theory	claim
51	184	Efficient 4D motion compensated lossless compression of dynamic volumetric medical image data	claim
52	184	A game theoretic framework for incentive-based peer-to-peer live-streaming social networks	claim
53	183	Segmentation of a speech spectrogram using mathematical morphology	claim
54	181	Joint tracking and video registration by factorial Hidden Markov models	claim
55	181	Finding needles in noisy haystacks	claim
56	180	Functional semi-automated segmentation of renal DCE-MRI sequences	claim
57	180	Air-coupled ultrasound time-of-flight estimation for shipping container cargo verification	claim
58	180	Adaptation of compressed HMM parameters for resource-constrained speech recognition	claim
59	178	Robust adaptive beamforming for general-rank signal models using positive semi-definite covariance constraint	claim
60	178	Coherent modulation filtering for speech	claim
61	177	Compressive coded aperture superresolution image reconstruction	claim
62	177	Iterative channel estimation and turbo equalization for time-varying OFDM systems	claim
63	177	Bandlimited signal reconstruction from noisy periodic nonuniform samples in time-interleaved ADCS	claim
64	177	BIC-based audio segmentation by divide-and-conquer	claim
65	177	Discriminative feature weighting using MCE training for topic identification of spoken audio recordings	claim
66	177	Accurate statistical spoken language understanding from limited development resources	claim
67	176	Multi-feature vector flow for active contour tracking	claim
68	175	Non-negative sparse image coder via simulated annealing and pseudo-inversion	claim
69	175	A new image denoising method based on the bilateral filter	claim
70	175	An improved mu-law proportionate NLMS algorithm	claim
71	174	Sparse and shift-invariant feature extraction from non-negative data	claim
72	174	Robust video fingerprints based on subspace embedding	claim
73	174	Gaze-contingent asr for spontaneous, conversational speech: An evaluation	claim
74	173	Blind deconvolution for sparse molecular imaging	claim
75	173	Maximum kernel density estimator for robust fitting	claim
76	173	Bounds and algorithms for time delay estimation on parallel, flat fading channels	claim
77	173	Belief propagation distributed estimation in sensor networks: An optimized energy accuracy tradeoff	claim
78	173	Unsupervised learning of auditory filter banks using non-negative matrix factorisation	claim
79	172	Blind deblurring of natural images	claim
80	172	Probabilistic framework for gene expression clustering validation based on gene ontology and graph theory	claim
81	172	A pattern classification framework for theoretical analysis of component forensics	claim
82	172	Optimized distributed 2D transforms for irregularly sampled sensor network grids using wavelet lifting	claim
83	172	The role of subspace swap in music performance breakdown	claim
84	172	High-performance scheduling algorithm for partially parallel LDPC decoder	claim
85	171	Graph laplacian for interactive image retrieval	claim
86	171	Human perception of synthetic character emotions in the presence of conflicting and congruent vocal and facial expressions	claim
87	171	Automatic lecture transcription by exploiting presentation slide information for language model adaptation	claim
88	171	Auction-based resource allocation for multi-relay asynchronous cooperative networks	claim
89	170	An ICA-based multilinear algebra tools for dimensionality reduction in hyperspectral imagery	claim
90	170	Cryptographic measures in information hiding	claim
91	170	Hierarchical lane detection for different types of roads	claim
92	169	Address assignment sensitive variable partitioning and scheduling for DSPS with multiple memory banks	claim
93	169	Anti-jam distributed MIMO decoding using wireless sensor networks	claim
94	169	Assessing the challenges of environmental signal processing through the sensorscope project	claim
95	168	Fine: Information embedding for document classification	claim
96	168	A method for locating multiple sources from a frame of a large-aperture microphone array data without tracking	claim
97	168	Throughput analysis of wireless mesh networks	claim
98	168	Distributed compressed sensing: Sparsity models and reconstruction algorithms using annihilating filter	claim
99	168	Compressed sensing - a look beyond linear programming	claim
100	167	Encoding large array signals into a 3D sound field representation for selective listening point audio based on blind source separation	claim
101	167	Toward a detector-based universal phone recognizer	claim
102	167	A novel a priori SNR estimation approach based on selective cepstro-temporal smoothing	claim
103	165	Accurate models for estimating area and power of FPGA implementations	claim
104	165	Blind source separation in a distributed microphone meeting environment for improved teleconferencing	claim
105	165	Non-iterative multiuser MIMO coordinated beamforming with limited feedforward	claim
106	165	Blind maximum-likelihood data recovery in OFDM	claim
107	165	Automatic classification of question turns in spontaneous speech using lexical and prosodic evidence	claim
108	164	An information theoretic approach to processing management	claim
109	164	Extracting clues from human interpreter speech for spoken language translation	claim
110	164	Recognition for synthesis: Automatic parameter selection for resynthesis of emotional speech from neutral speech	claim
111	163	On quantifying the effects of noncircularity on the complex fastica algorithm	claim
112	163	Efficient channel quantization scheme for multi-user MIMO broadcast channels with RBD precoding	claim
113	163	Link throughput of multi-channel opportunistic access with limited sensing	claim
114	162	Distributed multi-dimensional hidden Markov models for image and trajectory-based video classifications	claim
115	161	Symbol graph based discriminative training and rescoring for improved math symbol recognition	claim
116	161	Distributed stereo image coding with improved disparity and noise estimation	claim
117	161	Audio authentication based on distributed source coding	claim
118	161	A compressed sensing technique for OFDM channel estimation in mobile environments: Exploiting channel sparsity for reducing pilots	claim
119	161	Discriminative training by iterative linear programming optimization	claim
120	161	Effective error prediction using decision tree for ASR grammar network in call system	claim
121	161	Improved GMM-based language recognition using constrained MLLR transforms	claim
122	161	Modeling the intonation of discourse segments for improved online dialog ACT tagging	claim
123	160	Complexity modeling of scalable video decoding	claim
124	160	A nonparametric minimum entropy image deblurring algorithm	claim
125	160	A detection algorithm for zero-quantized DCT coefficients in JPEG	claim
126	160	An instantaneous vector representation of delta pitch for speaker-change prediction in conversational dialogue systems	claim
127	159	Compressed sensing radar	claim
128	159	Bootstrap tests for the time constancy of multifractal attributes	claim
129	159	Alternatives to the discrete fourier transform	claim
130	159	Application of sparse signal recovery to pilot-assisted channel estimation	claim
131	159	Layered wireless video multicast using omni-directional relays	claim
132	159	Kerdock codes for limited feedback MIMO systems	claim
133	159	Confidence estimation, OOV detection and language ID using phone-to-word transduction and phone-level alignments	claim
134	159	An iterative unsupervised learning method for information distillation	claim
135	158	Target detection and identification using canonical correlation analysis and subspace partitioning	claim
136	158	An unsupervised web-based topic language model adaptation method	claim
137	158	French prominence: A probabilistic framework	claim
138	158	Optimizing the acoustic modeling from an unbalanced bi-lingual corpus	claim
139	157	Adaptive RR prediction for cardiac MRI	claim
140	157	A factorization method in stereo motion for non-rigid objects	claim
141	157	Implementing communications systems on an SDR SoC	claim
142	157	Doppler-variant modeling of the vocal tract	claim
143	156	Secure wireless communications: Secret keys through multipath	claim
144	156	Avoiding divergence in the constant modulus algorithm	claim
145	156	Time-frequency localization from sparsity constraints	claim
146	155	Image interpolation with directionlets	claim
147	155	Mutual features for robust identification and verification	claim
148	155	A generalized optimal correlating transform for multiple description coding and its theoretical analysis	claim
149	155	Universal background model based speech recognition	claim
150	155	Combining open vocabulary recognition and word confusion networks	claim
151	154	Representation of solo clarinet music by physical modeling synthesis	claim
152	154	SURE-LET multichannel image denoising: undecimated wavelet thresholding	claim
153	154	Semantic composition process in a speech understanding system	claim
154	154	Analysis-by-synthesis features for speech recognition	claim
155	154	Speech denoising using nonnegative matrix factorization with priors	claim
156	153	Deformable trellis: open contour tracking in bio-image sequences	claim
157	153	Blind estimation of reverberation time based on the distribution of signal decay rates	claim
158	153	Query by humming of midi and audio using locality sensitive hashing	claim
159	153	Visual-aural attention modeling for talk show video highlight detection	claim
160	152	Robust correlation analysis with an application to functional MRI	claim
161	152	Efficient calculation of adaptive interpolation filter with distortion modelling	claim
162	152	A new implementation of trellis coded quantization based data hiding	claim
163	152	Approximation and resampling of tapped delay line channel models with guaranteed channel properties	claim
164	152	Energy efficient change detection over a MAC using physical layer fusion	claim
165	152	LSF mapping for voice conversion with very small training sets	claim
166	151	Controlling the false discovery rate in modeling brain functional connectivity	claim
167	151	Least-squares design of subsampled allpass transformed DFT filter-banks with LTI property	claim
168	151	Temporal selective dereverberation of noisy speech using one microphone	claim
169	150	A study of using locality preserving projections for feature extraction in speech recognition	claim
170	150	Fast noise tracking based on recursive smoothing of MMSE noise power estimates	claim
171	150	Some properties of an empirical mode type signal decomposition algorithm	claim
172	150	Punctuating speech for information extraction	claim
173	149	Modified polyphone decision tree specialization for porting multilingual Grapheme based ASR systems to new languages	claim
174	149	Language modeling for voice search: A machine translation approach	claim
175	149	An improved SNR estimator for speech enhancement	claim
176	149	The role of voice source measures on automatic gender classification	claim
177	148	Onset detection in pitched non-percussive music using warping-compensated correlation	claim
178	148	Optical flow robust estimation in a hybrid multi-resolution MRF framework	claim
179	148	Properties of the MIMO radar ambiguity function	claim
180	148	Distributed average consensus in sensor networks with quantized inter-sensor communication	claim
181	148	Cooperative MIMO-beamforming for multiuser relay networks	claim
182	148	Discriminative learning for optimizing detection performance in spoken language recognition	claim
183	148	Maximum conditional likelihood linear regression and maximum a posteriori for hidden conditional random fields speaker adaptation	claim
184	147	Blind source separation using monochannel overcomplete dictionaries	claim
185	146	Detecting music in ambient audio by long-window autocorrelation	claim
186	146	Sigma-delta resolution enhancement for far-field acoustic source separation	claim
187	146	Compressed sensing with sequential observations	claim
188	146	Design of block-structured LDPC codes for iterative receivers with soft sphere detection	claim
189	145	Smooth sigmoid wavelet shrinkage for non-parametric estimation	claim
190	145	Multisensor multiband cross-energy tracking for feature extraction and recognition	claim
191	145	Fast speaker adaptation using non-negative matrix factorization	claim
192	145	Audiovisual discrimination between laughter and speech	claim
193	144	Oracle estimation of adaptive cosine packet transforms for underdetermined audio source separation	claim
194	144	Music preference learning with partial information	claim
195	144	Topic mining on web-shared videos	claim
196	144	Blind channel estimation in DS-CDMA systems with unknown wide-sense stationary noise using generalized correlation decomposition	claim
197	144	Analytic framework for performance evaluation of multi-antenna WIMAX systems over fading channel	claim
198	144	Modulation decompositions for the interpolation of long gaps in acoustic signals	claim
199	144	From the multiple frequency tracker to the multiple frequency smoother	claim
200	143	Video denoising using a spatiotemporal statistical model of wavelet coefficients	claim
201	143	Sparse reconstruction by separable approximation	claim
202	142	Environmental sound recognition using MP-based features	claim
203	142	Cramer-Rao lower bound on doppler frequency of coherent pulse trains	claim
204	142	Brute-forcing hierarchical functionals for paralinguistics: A waste of feature space?	claim
205	142	An empirical study of automatic accent classification	claim
206	141	Path-constrained partial music synchronization	claim
207	141	Fast automated stopping-time and edge-strength estimation for anisotropic diffusion	claim
208	141	Maximum a posteriori ICA: Applying prior knowledge to the separation of acoustic sources	claim
209	141	Model-based sparsity projection pursuit for lattice vector quantization	claim
210	141	Fusion of cleavage site detection and pairwise alignment for fast subcellular localization	claim
211	141	A factor graph approach to joint iterative data detection and channel estimation in pilot-assisted IDMA transmissions	claim
212	141	Factorized variational approximations for acoustic multi source localization	claim
213	141	Robust kernel density estimation	claim
214	141	Adaptive score normalization for progressive model adaptation in text independent speaker verification	claim
215	141	Listener detection of talker stress in low-rate coded speech	claim
216	140	Adaptable K-nearest neighbor for image interpolation	claim
217	140	Impact of mismatched statistics on correlated MIMO capacity	claim
218	140	A comparative study of probabilistic ranking models for spoken document summarization	claim
219	140	Robust adaptive beamforming using sequential quadratic programming	claim
220	139	Robust pose estimation based on Sylvester's equation: Single and multiple collaborative cameras	claim
221	139	Fast query by example of environmental sounds via robust and efficient cluster-based indexing	claim
222	139	Learning to satisfy	claim
223	139	Adaptive resolution-constrained scalar multiple-description coding	claim
224	139	Exploiting contextual information for improved phoneme recognition	claim
225	139	A GIS-like training algorithm for log-linear models with hidden variables	claim
226	139	Using variational bayes free energy for unsupervised voice activity detection	claim
227	139	Subspace compressive detection for sparse signals	claim
228	138	Source coding with intermittent and degraded side information at the decoder	claim
229	138	Temporal masking for bit-rate reduction in audio codec based on Frequency Domain Linear Prediction	claim
230	138	Imaging concert hall acoustics using visual and audio cameras	claim
231	138	Universal switching portfolios under transaction costs	claim
232	137	Scalable H.264 wireless video transmission using quasi-orthogonal space-time block codes	claim
233	137	Online tracking of the degree of nonlinearity within complex signals	claim
234	137	Performance evaluation for tracking algorithms using object labels	claim
235	137	Hybrid design of filtered-x adaptive algorithm via sampled-data control theory	claim
236	137	Robust speaker identification using combined feature selection and missing data recognition	claim
237	136	Forensic techniques for classifying scanner, computer generated and digital camera images	claim
238	136	A constrained coefficient ica algorithm for group difference enhancement	claim
239	136	Impact of channel estimation error on performance of adaptive MIMO systems	claim
240	136	Efficient language model look-ahead probabilities generation using lower order LM look-ahead information	claim
241	136	Decentralized set-membership adaptive estimation for clustered sensor networks	claim
242	136	A covariance kernel for SVM language recognition	claim
243	135	Utility-based power control for peer-to-peer cognitive radio networks with heterogeneous QoS constraints	claim
244	135	Predictive fusion coding of spatio-temporally correlated sources	claim
245	135	A comparison of phone and grapheme-based spoken term detection	claim
246	135	A top-down auditory attention model for learning task dependent influences on prominence detection in speech	claim
247	134	Blind audiovisual separation based on redundant representations	claim
248	134	Robust speaker identification using auditory features and computational auditory scene analysis	claim
249	134	Position location by time reversal in communication networks	claim
250	134	Outage capacity of a cooperative scheme with binary input and a simple relay	claim
251	134	Composite hypothesis testing by optimally distinguishable distributions	claim
252	134	HMM adaptation using a phase-sensitive acoustic distortion model for environment-robust speech recognition	claim
253	134	A minimum-mean-square-error noise reduction algorithm on Mel-frequency cepstra for robust speech recognition	claim
254	133	A confidence measure and iterative rank-based method for temporal registration	claim
255	133	High-dynamic range compression using a fast multiscale optimization	claim
256	133	Filter bank design based on minimization of individual aliasing terms for minimum mutual information subband adaptive beamforming	claim
257	133	Collusion-aware traitor tracing in multimedia fingerprinting using sparse signal approximation	claim
258	133	Minimum variance multiplexing of multimedia objects	claim
259	133	An audio watermarking method based on molecular matching pursuit	claim
260	133	Minimum mean bayes risk error quantization of prior probabilities	claim
261	133	Distributed average consensus with increased convergence rate	claim
262	133	Distributed Kalman filtering based on quantized innovations	claim
263	133	Blind channel shortening in OFDM system using nulltones and cyclic prefix	claim
264	133	Stability analysis of the consensus-based distributed LMS algorithm	claim
265	133	Learning with noisy supervision for Spoken Language Understanding	claim
266	133	Dual-microphone speech dereverberation using GARCH modeling	claim
267	133	Rhetorical-State Hidden Markov Models for extractive speech summarization	claim
268	132	Speaker indexing and speech enhancement in real meetings / conversations	claim
269	132	Stability analysis of complex maximum likelihood ica using Wirtinger calculus	claim
270	132	Analytical driving functions for higher order Ambisonics	claim
271	132	Fast perfect weighted resampling	claim
272	132	Compressive wireless arrays for bearing estimation	claim
273	132	Live search for mobile: Web services by voice on the cellphone	claim
274	132	Impact of automatic sentence segmentation on meeting summarization	claim
275	132	On-demand new word learning using world wide web	claim
276	131	On security-aware transmission scheduling	claim
277	131	AN EM-based probabilistic approach for Acoustic Echo Suppression	claim
278	131	Video denoising using higher order optimal space-time adaptation	claim
279	131	Robust watermarking of 3D skinning mesh animations	claim
280	131	Contextually adaptive signal representation using conditional principal component analysis	claim
281	131	Rate-adaptive codes for the entire Slepian-Wolf region and arbitrarily correlated sources	claim
282	131	Investigating automatic assessment of reading comprehension in young children	claim
283	131	Fine-grained pitch accent and boundary tone labeling with parametric F0 features	claim
284	131	Joint dynamic resource allocation and waveform adaptation in cognitive radio networks	claim
285	131	Constrained nonlinear minimum mse estimation	claim
286	131	Maximum likelihood approach to speech enhancement for noisy reverberant signals	claim
287	131	Polyphase speech recognition	claim
288	130	Efficient assignment algorithm for mapping multidimensional signals into the physical memory	claim
289	130	Phonetic pronunciations for arabic speech-to-text systems	claim
290	130	A fast approximate joint diagonalization algorithm using a criterion with a block diagonal weight matrix	claim
291	130	Discrete rate spectral efficiency for adaptive MIMO systems	claim
292	130	Language recognition with discriminative keyword selection	claim
293	130	Interactive environmental sensing: Signal and image processing challenges	claim
294	129	Detecting mild cognitive loss with continuous monitoring of medication adherence	claim
295	129	Audio retrieval by latent perceptual indexing	claim
296	129	Decoding real-field codes by an iterative Expectation-Maximization (EM) algorithm	claim
297	129	Joint optimization of transceivers with fractionally spaced equalizers	claim
298	129	Text-independent voice conversion based on state mapped codebook	claim
299	129	Confidence scores for acoustic model adaptation	claim
300	128	Modulation forensics for wireless digital communications	claim
301	128	Denoising intra-coded moving pictures using motion estimation and pixel shift	claim
302	128	Bringing diverse classifiers to common grounds: dtransform	claim
303	128	Relation between joint optimizations for multiuser MIMO uplink and downlink with imperfect CSI	claim
304	128	Irrelevant variability normalization based HMM training using map estimation of feature transforms for robust speech recognition	claim
305	127	A first step to convolutive sparse representation	claim
306	127	On the synchrony of empirical mode decompositions with application to electroencephalography	claim
307	127	Caption-aided speech detection in videos	claim
308	127	Blind optimization of algorithm parameters for signal denoising by Monte-Carlo SURE	claim
309	127	Worst- and average-case complexity of LLL lattice reduction in MIMO wireless systems	claim
310	127	Quality evaluation of the G.EV-VBR speech codec	claim
311	127	High rate data hiding in ACELP speech codecs	claim
312	127	Weighted maximum likelihood autoregressive and moving average spectrum modeling	claim
313	126	Iterative R-D optimization of H.264	claim
314	126	Joint filterbank structures for integrating audio coding into hearing aid applications	claim
315	126	Matrix-based linear predictive compression of multi-channel surface emg signals	claim
316	125	Multiple kernel learning for speaker verification	claim
317	125	Probabilistic structural alignment of RNA sequences	claim
318	125	On ICA of complex-valued fMRI: Advantages and order selection	claim
319	125	Audio cover song identification based on tonal sequence alignment	claim
320	125	Variance reduction with neighborhood smoothing for local intrinsic dimension estimation	claim
321	125	Corrected tandem features for acoustic model training	claim
322	125	Stream weight tuning in dynamic Bayesian networks	claim
323	124	Parameterized design framework for hardware implementation of particle filters	claim
324	124	Robust video fingerprinting based on affine covariant regions	claim
325	124	Image processing by topological asymptotic analysis	claim
326	124	A realistic performance analysis for practical channel-aware scheduling	claim
327	124	Localization of multiple speakers based on a two step acoustic map analysis	claim
328	124	Mothers, adults, children, pets - towards the acoustics of intimacy	claim
329	124	Identification of linear systems with adaptive control of the cross-multiplicative transfer function approximation	claim
330	124	Maximum entropy models for speech confidence estimation	claim
331	124	Extracting question/answer pairs in multi-party meetings	claim
332	123	Density geodesics for similarity clustering	claim
333	123	A new Particle Filtering algorithm with structurally optimal importance function	claim
334	123	A weighted subspace approach for improving bagging performance	claim
335	123	Ultrasonic Doppler sensor for speaker recognition	claim
336	122	Bayesian extensions to non-negative matrix factorisation for audio signal modelling	claim
337	122	Audio-driven human body motion analysis and synthesis	claim
338	122	Towards the use of full covariance models for missing data speaker recognition	claim
339	121	The probability of near midair collisions using level-crossings	claim
340	121	Nonnegative Tucker decomposition with alpha-divergence	claim
341	121	Low-rank covariance matrix tapering for robust adaptive beamforming	claim
342	121	Approximate lower bounds for rate-distortion in compressive sensing systems	claim
343	121	Using dialogue acts to learn better repair strategies for spoken dialogue systems	claim
344	120	Fourier and filterbank analyses of signal-dependent noise	claim
345	120	Non-robustness of statistics-based beamformer design in correlated MIMO channels	claim
346	120	Exploiting temporal change of pitch in formant estimation	claim
347	119	Subband conversion for feature extraction from compressed audio	claim
348	119	Harmonic and inharmonic Nonnegative Matrix Factorization for Polyphonic Pitch transcription	claim
349	119	Systematic generation of FPGA-based FFT implementations	claim
350	119	Dealing with uncertainty in microphone placement in a microphone array speech recognition system	claim
351	119	Maximum likelihood binary detection in improper complex gaussian noise	claim
352	119	System combination using auxiliary information for speaker verification	claim
353	119	Multilingual weighted codebooks	claim
354	119	Overlapped speech detection for improved speaker diarization in multiparty meetings	claim
355	118	On the capacity of orientation modulation halftone channels	claim
356	118	A Computationally Efficient Scheme for Dominant Harmonic Source Separation	claim
357	118	A no-reference perceptual blockiness metric	claim
358	118	Efficient computation of the binary vector that maximizes a rank-deficient quadratic form	claim
359	117	Modeling regulatory sites with higher order position-dependent weight matrices	claim
360	117	Sound field decomposition using spherical microphone arrays	claim
361	117	Compressive sensing of parameterized shapes in images	claim
362	117	Perceptsynth: mapping perceptual musical features to sound synthesis parameters	claim
363	117	Nonparametric feature normalization for SVM-based speaker verification	claim
364	117	Objective perceptual quality assessment for self-steering binaural hearing aid microphone arrays	claim
365	117	Voice source cepstrum coefficients for speaker identification	claim
366	117	Speaker diarization of French broadcast news	claim
367	116	Learning the kernel via convex optimization	claim
368	116	Incremental salient point detection	claim
369	116	Null-Space representation for view-invariant motion trajectory classification-recognition and indexing-retrieval	claim
370	116	On persymmetric covariance matrices in adaptive detection	claim
371	116	Improving Spoken Language Understanding with information retrieval and active learning methods	claim
372	116	Ratio semi-definite classifiers	claim
373	116	Unsupervised validity measures for vocalization clustering	claim
374	115	Multiple fundamental frequency estimation using Gaussian smoothness	claim
375	115	On nonlinear transformations of stochastic variables and its application to nonlinear filtering	claim
376	115	Is voice transformation a threat to speaker identification?	claim
377	114	Generalized Improved Spread Spectrum watermarking robust against translation attacks	claim
378	114	Multi-source DOA estimation in a reverberant room	claim
379	114	Low-complexity receivers for multiuser detection with an unknown number of active users	claim
380	114	The role of subspace swap in maximum likelihood estimation performance breakdown	claim
381	114	Scalable distributed Kalman filtering through consensus	claim
382	114	Frame-based acoustic feature integration for speech understanding	claim
383	114	Referential semantic language modeling for data-poor domains	claim
384	114	Multi-stream parameterization for structural speech recognition	claim
385	113	Satellite image reconstruction from an irregular sampling	claim
386	113	Adaptive detection for a differential chaos-based multiple access system on unknown multipath fading channels	claim
387	113	Stable sparse approximations via nonconvex optimization	claim
388	113	Maximum-likelihood period estimation from sparse, noisy timing data	claim
389	113	Deploying GOOG-411: Early lessons in data, measurement, and testing	claim
390	112	Automatic synthesis of VLSI architectures for arbitrary lifting-based filter banks and transforms	claim
391	112	Evaluation of several strategies for single sensor speech/music separation	claim
392	112	Extension of EFICA algorithm for blind separation of piecewise stationary non Gaussian sources	claim
393	112	Blind channel estimation in MIMO-OFDM systems using semi-definite relaxation	claim
394	112	A multi-class MLLR kernel for SVM speaker recognition	claim
395	111	A robust method for QRS detection based on modified p-spectrum	claim
396	111	Unsupervised discriminative adaptation using discriminative mapping transforms	claim
397	111	Can voice quality improve mandarin tone recognition?	claim
398	111	Statistical approach to vocal tract transfer function estimation based on factor analyzed trajectory HMM	claim
399	110	ITU-T G.EV-VBR baseline codec	claim
400	110	Recasting the discriminative n-gram model as a pseudo-conventional n-gram model for LVCSR	claim
401	109	Trajectory inverse kinematics by nonlinear, nongaussian tracking	claim
402	109	Implementation of message-passing algorithms for the acquisition of spreading codes	claim
403	109	Recent results of rainfall mapping from cellular network measurements	claim
404	109	Competitive design of multiuser MIMO interference systems based on game theory: A unified framework	claim
405	109	Scalable OFDM design for underwater acoustic communications	claim
406	109	Analyzing the scalability of SIMD for the next generation software defined radio	claim
407	109	Improving the modeling of the noise part in the harmonic plus noise model of speech	claim
408	108	On the tradeoff between security and Robustness of the Trellis Coded Quantization scheme	claim
409	108	Phase singularities for image representation and matching	claim
410	108	An iterative spatio-temporal speech enhancement algorithm for microphone arrays	claim
411	108	Nonstationary multiple-antenna interference cancellation for unsynchronized OFDM systems with distributed training	claim
412	108	Exploiting dialogue act tagging and prosodic information for action item identification	claim
413	108	Modulation analysis of speech through orthogonal FIR filterbank optimization	claim
414	107	Determining the parameters in regularized super-resolution reconstruction	claim
415	107	Generic and typical ranks of three-way arrays	claim
416	107	Gradient steepness metrics using extended Baum-Welch transformations for universal pattern recognition tasks	claim
417	106	A tempo-insensitive distance measure for cover song identification based on chroma features	claim
418	106	A new class of lifting wavelet transform for guaranteeing losslessness of specific signals	claim
419	106	Admissible stopping in viterbi beam search for unit selection in concatenative speech synthesis	claim
420	105	Towards optimal design of signal fingerprinting codes	claim
421	105	Single sideband encoder for music coding in cochlear implants	claim
422	105	Combination of strongly and weakly constrained recognizers for reliable detection of OOVS	claim
423	105	Signal approximation using the bilinear transform	claim
424	105	Sequential experimental design for misspecified nonlinear models	claim
425	104	Musical Sound Separation Using Pitch-Based Labeling and Binary Time-Frequency Masking	claim
426	104	Reconstructing sparse signals from their zero crossings	claim
427	104	Directional dependency of cepstrum on vocal tract length	claim
428	104	Name-aware speech recognition for interactive question answering	claim
429	104	Performance evaluation of the speaker-independent HMM-based speech synthesis system "HTS 2007" for the Blizzard Challenge 2007	claim
430	104	A factor-analysis decoder for high-performance neural prostheses	claim
431	104	Stylization of pitch with syllable-based linear segments	claim
432	103	An interactive hybrid programming approach to signals and systems laboratory	claim
433	103	Computationally efficient equalization of room impulse responses robust to system estimation errors	claim
434	103	Sentence segmentation and punctuation recovery for spoken language translation	claim
435	102	Robust image registration with illumination, blur and noise variations for super-resolution	claim
436	102	On the optimality of ideal binary time-frequency masks	claim
437	102	Some results on 16-QAM MIMO detection using semidefinite relaxation	claim
438	102	Estimating the dominant person in multi-party conversations using speaker diarization strategies	claim
439	101	A two-layered trellis approach to audio encoding	claim
440	101	Single-channel speech separation based on modulation frequency	claim
441	101	Speech privacy for modern mobile communication systems	claim
442	101	Nonnegative matrix factorization for real time musical analysis and sight-reading evaluation	claim
443	101	Signal masking in Gaussian channels	claim
444	101	Cepstral domain feature compensation based on diagonal approximation	claim
445	101	Tracking analysis of the constant modulus algorithm	claim
446	100	Newton method for the ICA mixture model	claim
447	100	Frequency domain selective tap adaptive algorithms for sparse system identification	claim
448	100	Joint Bayesian positioning and multipath mitigation in GNSS	claim
449	100	Double-differential coding for orthogonal space-time block codes	claim
450	100	Environment-invariant compensation for reverberation using linear post-filtering for minimum distortion	claim
451	100	Iterative extrapolation algorithm for data reconstruction over sphere	claim
452	99	Image spam hunter	claim
453	99	Cross-correlation of beat-synchronous representations for music similarity	claim
454	99	Mode sign estimation to improve source depth estimation	claim
455	99	Information theoretic bounds on neural prosthesis effectiveness: The importance of spike sorting	claim
456	98	Rhythmic similarity of music based on dynamic periodicity warping	claim
457	98	Portuguese variety identification on broadcast news	claim
458	97	An invertible quantization based watermarking approach	claim
459	97	Learning max-weight discriminative forests	claim
460	97	NeSh: A joint shadowing model for links in a multi-hop network	claim
461	97	Complex-valued sparse representation based on smoothed l0 norm	claim
462	97	Empirical properties of multilingual phone-to-word transduction	claim
463	96	Second-order near-field localization with automatic paring operation	claim
464	96	Adaptive short-time analysis-synthesis for speech enhancement	claim
465	96	Localized spectro-temporal cepstral analysis of speech	claim
466	95	Robust design of wideband loudspeaker arrays	claim
467	95	Broadcast news subtitling system in Portuguese	claim
468	95	Joint source-channel mappings for the relay channel	claim
469	95	Average case analysis of sparse recovery with thresholding : New bounds based on average dictionary coherence	claim
470	94	Nonlinear residual acoustic echo suppression for high levels of harmonic distortion	claim
471	94	Turbo-coded decode-and-forward strategy resilient to relay errors	claim
472	94	Target-oriented phone tokenizers for spoken language recognition	claim
473	93	Optimal FDMA over wireless fading mobile ad-hoc networks	claim
474	92	Performance and robustness: A trade-off in dynamic signature verification	claim
475	92	Reproducing kernel Hilbert spaces for spike train analysis	claim
476	91	Image deconvolution under poisson noise using sparse representations and proximal thresholding iteration	claim
477	90	Joint base-calling of two DNA sequences with factor graphs	claim
478	89	Robust multiuser detection based on probability constrained optimization of the MMSE receiver	claim
479	89	Target talker enhancement in hearing devices	claim
480	86	Speech enhancement using a pitch predictive model	claim
481	85	Tree-guided transformation-based homograph disambiguation in Mandarin TTS system	claim
482	82	Performance evaluation of distributed video coding schemes	claim
483	81	A cheap relaying protocol for orthogonal relay channels	claim
484	80	Structure of non-binary regular ldpc cycle codes	claim
485	80	Theoretical statistical correlation for biometric identification performance	claim
486	80	Parsing-based objective functions for speech recognition in translation applications	claim
487	80	A turbo-style algorithm for lexical baseforms estimation	claim
488	77	The extended invariance principle applied to joint time-delay, frequency, and DOA estimation	claim
489	75	Performance analysis of the cepstral technique for frequency-domain optical-coherence tomography	claim
490	69	Substituting the cumulants in the super-exponential blind equalization algorithm	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers