Sciweavers

ICASSP
2008
IEEE
14 years 2 months ago
Temporal masking for bit-rate reduction in audio codec based on Frequency Domain Linear Prediction
Audio coding based on Frequency Domain Linear Prediction (FDLP) uses auto-regressive model to approximate Hilbert envelopes in frequency sub-bands for relatively long temporal seg...
Sriram Ganapathy, Petr Motlícek, Hynek Herm...
ICASSP
2008
IEEE
14 years 2 months ago
French prominence: A probabilistic framework
Identification of prosodic phenomena is of first importance in prosodic analysis and modeling. In this paper, we introduce a new method for automatic prosodic phenomena labellin...
Nicolas Obin, Xavier Rodet, Anne Lacheret-Dujour
ICASSP
2008
IEEE
14 years 2 months ago
Adaptation of compressed HMM parameters for resource-constrained speech recognition
Recently, we successfully developed and reported a new unsupervised online adaptation technique, which jointly compensates for additive and convolutive distortions with vector Tay...
Jinyu Li, Li Deng, Dong Yu, Jian Wu, Yifan Gong, A...
ICASSP
2008
IEEE
14 years 2 months ago
Robust speaker identification using combined feature selection and missing data recognition
Missing data techniques have been recently applied to speaker recognition to increase performance in noisy environments. The drawback of these techniques is the vulnerability of t...
Daniel Pullella, Marco Kühne, Roberto Togneri
ICASSP
2008
IEEE
14 years 2 months ago
Perceptually weighted distortion measures and the tandem connection of speech codecs
Tandem connections of voice codecs can occur today in mobileto-mobile calls and for certain VoIP connections. While postfiltering in tandem encodings is well-understood, the effe...
Niranjan Shetty, Jerry D. Gibson
ICASSP
2008
IEEE
14 years 2 months ago
Identification of linear systems with adaptive control of the cross-multiplicative transfer function approximation
In this paper, we extend the cross-multiplicative transfer function (CMTF) approach for improved system identification in the shorttime Fourier transform (STFT) domain. The propo...
Yekutiel Avargel, Israel Cohen
ICASSP
2008
IEEE
14 years 2 months ago
Composite hypothesis testing by optimally distinguishable distributions
Relying on optimally distinguishable distributions (ODD), it was defined very recently a new framework for the composite hypothesis testing. We resort to the linear model to inve...
Seyed Alireza Razavi, Ciprian Doru Giurcaneanu
ICASSP
2008
IEEE
14 years 2 months ago
Recognition for synthesis: Automatic parameter selection for resynthesis of emotional speech from neutral speech
One of the biggest challenges in emotional speech resynthesis is the selection of modification parameters that will make humans perceive a targeted emotion. The best selection me...
Murtaza Bulut, Sungbok Lee, Shrikanth Narayanan
ICASSP
2008
IEEE
14 years 2 months ago
Audiovisual discrimination between laughter and speech
Past research on automatic laughter detection has focused mainly on audio-based detection. Here we present an audiovisual approach to distinguishing laughter from speech and we sh...
Stavros Petridis, Maja Pantic