Reverberation Model-Based Decoding in the Logmelspec Domain for Robust Distant-Talking Speech Recognition

Sehr, Armin; Maas, Roland; Kellermann, Walter

doi:10.1109/tasl.2010.2050511

Cited by 53 publications

(35 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However there has been less work in applying model-based approaches to handle reverberant noise. The majority of schemes for handling reverberant noise are enhancement-based [3,4], and extensions to handle the additional uncertainty [3,5].…”

Section: Introductionmentioning

confidence: 99%

Model-based approaches to handling additive noise in reverberant environments

Gales

Wang

2011

2011 Joint Workshop on Hands-Free Speech Communication and Microphone Arrays

View full text Add to dashboard Cite

Model-based approaches to handle additive and convolutional noise have been extensively investigated and used. However, the application of these approaches to handling reverberant noise has received less attention. This paper examines the extension of two standard adaptation/compensation approaches to handling reverberant noise. The first is an extension of vector Taylor series (VTS) compensation, reverberant VTS, where a mismatch function representing reverberant noise is used. The second scheme modifies constrained MLLR to allow a wide-span of frames to be taken into account and "projected" into the required dimensionality. To allow additive noise to be handled, both these schemes are combined with standard VTS. The approaches are evaluated and compared on two tasks, MC-WSJ-AV, and a reverberant simulated version of AURORA-4.

show abstract

Section: Introductionmentioning

confidence: 99%

Model-based approaches to handling additive noise in reverberant environments

Gales

Wang

2011

2011 Joint Workshop on Hands-Free Speech Communication and Microphone Arrays

View full text Add to dashboard Cite

show abstract

“…In recent studies for robust speech recognition and speech dereverberation, the reverberant speech in the STFT (Short-Term Fourier Transform) domain is often modeled so that each frequency bin of the reverberant speech is represented by the convolution of the frame sequences of clean speech and the acoustic transfer function [21,22].…”

Section: Cepstrum Representation Of Reverberant Speechmentioning

confidence: 99%

Evaluation of an Active Microphone with a Parabolic Reflection Board for Monaural Sound-Source-Direction Estimation

Takiguchi¹,

Takashima²,

Ariki³

2014

Soundscape Semiotics - Localisation and Categorisation

View full text Add to dashboard Cite

“…In recent studies on robust speech recognition and speech dereverberation, the reverberant speech in the shortterm Fourier transform (STFT) domain is often modeled so that each frequency bin of the reverberant speech is represented by the convolution of the frame sequences of clean speech and the acoustic transfer function as follows [15,16].…”

Section: Cepstrum Representation Of Reverberant Speechmentioning

confidence: 99%

Single-channel talker localization based on separation of the acoustic transfer function using hidden Markov model and its classification

Takashima

Takiguchi

Ariki

2013

Acoust. Sci. & Tech.

View full text Add to dashboard Cite

This paper presents a talker localization method using only a single microphone, where phoneme hidden Markov models (HMMs) of clean speech are introduced to estimate the acoustic transfer function from the user's position. In our previous work, we proposed a Gaussian mixture model (GMM) separation for estimation of the user's position, where the observed speech is separated into the acoustic transfer function and the clean speech GMM. In this paper, we propose an improved method using phoneme HMMs for separation of the acoustic transfer function. This method expresses the speech signal as a network of phoneme HMMs, while our previous method expresses it as a GMM without considering the temporal phonetic changes of the speech signal. The support vector machine (SVM) for classifying the user's position is trained using the separated frame sequences of the acoustic transfer function. Then, for each test data set, the acoustic transfer function is separated, and the position is estimated by discriminating the acoustic transfer function. The effectiveness of this method has been confirmed by talker localization experiments performed in a room environment.

show abstract

Reverberation Model-Based Decoding in the Logmelspec Domain for Robust Distant-Talking Speech Recognition

Cited by 53 publications

References 25 publications

Model-based approaches to handling additive noise in reverberant environments

Model-based approaches to handling additive noise in reverberant environments

Evaluation of an Active Microphone with a Parabolic Reflection Board for Monaural Sound-Source-Direction Estimation

Single-channel talker localization based on separation of the acoustic transfer function using hidden Markov model and its classification

Contact Info

Product

Resources

About