Tomohiro Nakatani
Research Subjects
Tomohiro Nakatani has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Keisuke Kinoshita
NTT Communication Science Laboratories
4 shared publications - Masato Miyoshi
NTT Communication Science Laboratories
4 shared publications - Takuya Yoshioka
NTT Communication Science Laboratories
4 shared publications - Biing-Hwang Juang
Georgia Institute of Technology
3 shared publications Biing-Hwang Juang
School of ECE, Georgia Institute of Technology, Atlanta GA 30318 USA
2 shared publicationsKeisuke Kinoshita
NTT Communication Science Laboratories, NTT Corporation, Kyoto 619-0237 Japan
2 shared publications
Latest Publications
- 23 June 2011
- Published by Springer Nature
- p. 225-255
Variance Compensation for Recognition of Reverberant Speech with Dereverberation Preprocessing
- 23 June 2011
- Published by Springer Nature
- p. 225-255
Variance Compensation for Recognition of Reverberant Speech with Dereverberation Preprocessing
- 1 January 2010
- Published by Springer Nature
- p. 151-182
Speech Dereverberation and Denoising Based on Time Varying Speech Model and Autoregressive Reverberation Model
- 1 January 2010
- Published by Springer Nature
- p. 151-182
Speech Dereverberation and Denoising Based on Time Varying Speech Model and Autoregressive Reverberation Model
- 1 January 2010
- Published by Springer Nature
- p. 271-310
Inverse Filtering for Speech Dereverberation Without the Use of Room Acoustics Information
- 1 January 2010
- Published by Springer Nature
- p. 271-310
Inverse Filtering for Speech Dereverberation Without the Use of Room Acoustics Information
- 1 May 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 220-223
Speech Dereverberation in Short Time Fourier Transform Domain with Crossband Effect Compensation
It has recently been shown that the maximum likelihood estimation approach with a time-varying source model is very effective in achieving speech dereverberation based only on a short observation. In addition, STFT domain processing has been shown to be promising for implementing this dereverberation approach in a computationally efficient way. This paper presents a way of further improving the STFT domain speech dereverberation in terms of both computational cost and accuracy. One important issue here is how to calculate time-domain convolution with a long filter precisely using STFT. We introduce an STFT domain filtering method with crossband effect compensation for this purpose. Experimental results show that the proposed method allows us to implement the dereverberation algorithm in the STFT domain more precisely with less computational cost than the existing method.
- 1 May 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 220-223
Speech Dereverberation in Short Time Fourier Transform Domain with Crossband Effect Compensation
It has recently been shown that the maximum likelihood estimation approach with a time-varying source model is very effective in achieving speech dereverberation based only on a short observation. In addition, STFT domain processing has been shown to be promising for implementing this dereverberation approach in a computationally efficient way. This paper presents a way of further improving the STFT domain speech dereverberation in terms of both computational cost and accuracy. One important issue here is how to calculate time-domain convolution with a long filter precisely using STFT. We introduce an STFT domain filtering method with crossband effect compensation for this purpose. Experimental results show that the proposed method allows us to implement the dereverberation algorithm in the STFT domain more precisely with less computational cost than the existing method.
- 1 October 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 19311168,p. 299-302
Importance of Energy and Spectral Features in Gaussian Source Model for Speech Dereverberation
This paper introduces speech dereverberation based on a time-varying Gaussian source model (GSM) and investigates its behavior to provide a better perspective on solving the dereverberation problem. GSM is a generalization of the autocorrelation codebook (ACC) that has recently been shown to enable us to achieve high quality speech dereverberation with only a few seconds' observation. Based on GSM, the speech dereverberation is formulated as a likelihood maximization problem with multi-channel linear prediction, where the reverberant speech signal is transformed into one that is probabilistically more like clean speech. For investigation purposes, the autocorrelation matrix of the GSM is first decomposed into energy, vocal tract filter, and excitation signal features by adopting an autoregressive GSM (ARGSM), and then analyzed based on experiments. They reveal that the energy feature in the models plays a major role in reducing the reverberation components. It is also shown that the other spectral features in the models further contribute to the recovery of the short-time characteristics of the dereverberated signals.
- 1 October 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 19311168,p. 299-302
Importance of Energy and Spectral Features in Gaussian Source Model for Speech Dereverberation
This paper introduces speech dereverberation based on a time-varying Gaussian source model (GSM) and investigates its behavior to provide a better perspective on solving the dereverberation problem. GSM is a generalization of the autocorrelation codebook (ACC) that has recently been shown to enable us to achieve high quality speech dereverberation with only a few seconds' observation. Based on GSM, the speech dereverberation is formulated as a likelihood maximization problem with multi-channel linear prediction, where the reverberant speech signal is transformed into one that is probabilistically more like clean speech. For investigation purposes, the autocorrelation matrix of the GSM is first decomposed into energy, vocal tract filter, and excitation signal features by adopting an autoregressive GSM (ARGSM), and then analyzed based on experiments. They reveal that the energy feature in the models plays a major role in reducing the reverberation components. It is also shown that the other spectral features in the models further contribute to the recovery of the short-time characteristics of the dereverberated signals.
- 1 May 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 02714302,p. 2990-2993
Joint Source-Channel Modeling and Estimation for Speech Dereverberation
Speech dereverberation is an important challenge in acoustic signal processing because of the detrimental effects upon the signal quality brought by the reverberant components due to acoustic reflections from the walls of the room enclosure. Most of the methods proposed so far such as microphone array beamforming and room impulse response inversion for deconvolution make very little use of the knowledge about the characteristics of the source signal. This paper presents a formulation of speech dereverberation as a probabilistic modeling problem in which joint estimation of the source and the channel (or its inverse) can be accomplished. We discuss reasonable representations of the source prior for inclusion in such a formulation and propose the corresponding solutions.
- 1 May 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 02714302,p. 2990-2993
Joint Source-Channel Modeling and Estimation for Speech Dereverberation
Speech dereverberation is an important challenge in acoustic signal processing because of the detrimental effects upon the signal quality brought by the reverberant components due to acoustic reflections from the walls of the room enclosure. Most of the methods proposed so far such as microphone array beamforming and room impulse response inversion for deconvolution make very little use of the knowledge about the characteristics of the source signal. This paper presents a formulation of speech dereverberation as a probabilistic modeling problem in which joint estimation of the source and the channel (or its inverse) can be accomplished. We discuss reasonable representations of the source prior for inclusion in such a formulation and propose the corresponding solutions.
- 1 May 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 02714302,p. 2986-2989
Robust blind dereverberation of speech signals based on characteristics of short-time speech segments
This paper addresses blind dereverberation techniques based on the inherent characteristics of speech signals. Two challenging issues for speech dereverberation involve decomposing reverberant observed signals into colored sources and room transfer functions (RTFs), and making the inverse filtering robust as regards acoustic and system noise. We show that short-time speech characteristics are very important for this task, and that multi-channel linear prediction (MCLP) is a useful tool for achieving robust inverse filtering. As examples, we detail three recently proposed robust dereverberation methods. By assuming the source to be a small order autoregressive process, we can present an efficient source estimation method that reduces late reverberation reflections of the reverberation using multi-step linear prediction. By exploiting the time-varying nature of the speech signals, we can also develop a method that can estimate both the source and the inverse filters of the RTFs. Furthermore, we can achieve high quality speech dereverberation by formulating the problem as a likelihood maximization problem using a statistical speech model that represents the spectral characteristics of short-time speech segments including harmonicity.
- 1 May 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 02714302,p. 2986-2989
Robust blind dereverberation of speech signals based on characteristics of short-time speech segments
This paper addresses blind dereverberation techniques based on the inherent characteristics of speech signals. Two challenging issues for speech dereverberation involve decomposing reverberant observed signals into colored sources and room transfer functions (RTFs), and making the inverse filtering robust as regards acoustic and system noise. We show that short-time speech characteristics are very important for this task, and that multi-channel linear prediction (MCLP) is a useful tool for achieving robust inverse filtering. As examples, we detail three recently proposed robust dereverberation methods. By assuming the source to be a small order autoregressive process, we can present an efficient source estimation method that reduces late reverberation reflections of the reverberation using multi-step linear prediction. By exploiting the time-varying nature of the speech signals, we can also develop a method that can estimate both the source and the inverse filters of the RTFs. Furthermore, we can achieve high quality speech dereverberation by formulating the problem as a likelihood maximization problem using a statistical speech model that represents the spectral characteristics of short-time speech segments including harmonicity.
- 1 April 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, I-193-I-196
Study on Speech Dereverberation with Autocorrelation Codebook
This paper proposes a new speech dereverberation approach based on a statistical speech model. An autocorrelation codebook is introduced as a model that can represent time-varying short-time speech characteristics corresponding to the cepstrum and harmonics. The speech dereverberation is formulated as a likelihood maximization problem, in which the quality of a speech signal is recovered by turning the signal into one that is probabilistically more like a clean speech. Two dereverberation algorithms are derived based on different scenarios, regularized inversion and inverse filter estimation. Experimental results show that the proposed approach allows us to reduce both reverberation and noise with the regularized inversion, and to estimate inverse filters that can dereverberate signals effectively from just a small number of observed signals.
- 1 April 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, I-193-I-196
Study on Speech Dereverberation with Autocorrelation Codebook
This paper proposes a new speech dereverberation approach based on a statistical speech model. An autocorrelation codebook is introduced as a model that can represent time-varying short-time speech characteristics corresponding to the cepstrum and harmonics. The speech dereverberation is formulated as a likelihood maximization problem, in which the quality of a speech signal is recovered by turning the signal into one that is probabilistically more like a clean speech. Two dereverberation algorithms are derived based on different scenarios, regularized inversion and inverse filter estimation. Experimental results show that the proposed approach allows us to reduce both reverberation and noise with the regularized inversion, and to estimate inverse filters that can dereverberate signals effectively from just a small number of observed signals.
- 1 December 2004
- Published by Acoustical Society of America (ASA) in The Journal of the Acoustical Society of America
- Vol. 116 (6) , 3690-3700
Robust and accurate fundamental frequency estimation based on dominant harmonic components
This paper presents a new method for robust and accurate fundamental frequency estimation in the presence of background noise and spectral distortion. Degree of dominance and dominance spectrum are defined based on instantaneous frequencies. The degree of dominance allows one to evaluate the magnitude of individual harmonic components of the speech signals relative to background noise while reducing the influence of spectral distortion. The fundamental frequency is more accurately estimated from reliable harmonic components which are easy to select given the dominance spectra. Experiments are performed using white and babble background noise with and without spectral distortion as produced by a SRAEN filter. The results show that the present method is better than previously reported methods in terms of both gross and fine errors.- 1 December 2004
- Published by Acoustical Society of America (ASA) in The Journal of the Acoustical Society of America
- Vol. 116 (6) , 3690-3700
Robust and accurate fundamental frequency estimation based on dominant harmonic components
This paper presents a new method for robust and accurate fundamental frequency estimation in the presence of background noise and spectral distortion. Degree of dominance and dominance spectrum are defined based on instantaneous frequencies. The degree of dominance allows one to evaluate the magnitude of individual harmonic components of the speech signals relative to background noise while reducing the influence of spectral distortion. The fundamental frequency is more accurately estimated from reliable harmonic components which are easy to select given the dominance spectra. Experiments are performed using white and babble background noise with and without spectral distortion as produced by a SRAEN filter. The results show that the present method is better than previously reported methods in terms of both gross and fine errors.