Sciweavers

ICASSP
2008
IEEE
14 years 2 months ago
Computationally efficient equalization of room impulse responses robust to system estimation errors
Equalization techniques for room impulse responses (RIRs) are important in acoustic signal processing applications such as speech dereverberation. In practice, only approximate es...
Wancheng Zhang, Nikolay D. Gaubitch, Patrick A. Na...
ICASSP
2008
IEEE
14 years 2 months ago
Exploiting dialogue act tagging and prosodic information for action item identification
An important task for multiparty meeting understanding is extracting action items. Action items are a set of tasks that are agreed on by the participants for execution after the m...
Fan Yang, Gökhan Tür, Elizabeth Shriberg
ICASSP
2008
IEEE
14 years 2 months ago
An improved mu-law proportionate NLMS algorithm
In this paper, we propose an algorithm to improve the performance of the mu-law PNLMS algorithm (MPNLMS) for nonsparse impulse responses. Although the existing MPNLMS algorithm wa...
Ligang Liu, Masahiro Fukumoto, Sachio Saiki
ICASSP
2008
IEEE
14 years 2 months ago
Reproducing kernel Hilbert spaces for spike train analysis
This paper introduces a generalized cross-correlation (GCC) measure for spike train analysis derived from reproducing kernel Hilbert spaces (RKHS) theory. An estimator for GCC is ...
António R. C. Paiva, Il Park, Jose C. Princ...
ICASSP
2008
IEEE
14 years 2 months ago
Temporal selective dereverberation of noisy speech using one microphone
Reverberant speech can be described as sounding distant with noticeable coloration and echo. These detrimental perceptual effects are caused by early and late reflections, respec...
Emanuel A. P. Habets, Nikolay D. Gaubitch, Patrick...
ICASSP
2008
IEEE
14 years 2 months ago
Target-oriented phone tokenizers for spoken language recognition
This paper presents a new strategy for designing the parallel phone recognizers for spoken language recognition. Given a collection of parallel phone recognizers, we select a subs...
Rong Tong, Bin Ma, Haizhou Li, Engsiong Chng
ICASSP
2008
IEEE
14 years 2 months ago
System combination using auxiliary information for speaker verification
Recent studies in speaker recognition have shown that scorelevel combination of subsystems can yield significant performance gains over individual subsystems. We explore the use ...
Luciana Ferrer, Martin Graciarena, Argyrios Zymnis...
ICASSP
2008
IEEE
14 years 2 months ago
An unsupervised web-based topic language model adaptation method
This paper focuses on a solution to better adapt ASR systems, whose language models (LM) are usually trained on topic-independent corpora, to new topics, in particular in the case...
Gwénolé Lecorvé, Guillaume Gr...
ICASSP
2008
IEEE
14 years 2 months ago
Irrelevant variability normalization based HMM training using map estimation of feature transforms for robust speech recognition
In the past several years, we’ve been studying feature transformation (FT) approaches to robust automatic speech recognition (ASR) which can compensate for possible “distortio...
Donglai Zhu, Qiang Huo
ICASSP
2008
IEEE
14 years 2 months ago
Exploiting contextual information for improved phoneme recognition
In this paper, we investigate the significance of contextual information in a phoneme recognition system using the hidden Markov model - artificial neural network paradigm. Cont...
Joel Pinto, B. Yegnanarayana, Hynek Hermansky, Mat...