Hidden Markov model training with contaminated speech material for distant-talking speech recognition

Matassoni, Marco; Omologo, Maurizio; Giuliani, Diego; Svaizer, Piergiorgio

doi:10.1006/csla.2002.0191

Cited by 32 publications

(16 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Some data sets were based on simulations realized applying a contamination method [20,21,22] that combines clean-speech signals, estimated Impulse Responses (IRs), and real multichannel background noise sequences, as described in [18]. Other corpora were recorded under real-world conditions.…”

Section: Dirha Corporamentioning

confidence: 99%

See 1 more Smart Citation

The DIRHA-ENGLISH corpus and related tasks for distant-speech recognition in domestic environments

Ravanelli

Cristoforetti

Gretter

et al. 2015

2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)

Self Cite

View full text Add to dashboard Cite

This paper introduces the contents and the possible usage of the DIRHA-ENGLISH multi-microphone corpus, recently realized under the EC DIRHA project. The reference scenario is a domestic environment equipped with a large number of microphones and microphone arrays distributed in space.The corpus is composed of both real and simulated material, and it includes 12 US and 12 UK English native speakers. Each speaker uttered different sets of phonetically-rich sentences, newspaper articles, conversational speech, keywords, and commands. From this material, a large set of 1-minute sequences was generated, which also includes typical domestic background noise as well as inter/intra-room reverberation effects. Dev and test sets were derived, which represent a very precious material for different studies on multi-microphone speech processing and distant-speech recognition. Various tasks and corresponding Kaldi recipes have already been developed.The paper reports a first set of baseline results obtained using different techniques, including Deep Neural Networks (DNN), aligned with the state-of-the-art at international level.

show abstract

Section: Dirha Corporamentioning

confidence: 99%

“…The DIRHA-ENGLISH simulated data sets derive from the clean speech described in Section 3.1, and from the application of the contamination method discussed in [20,30].…”

Section: Simulated Data Setmentioning

confidence: 99%

The DIRHA-ENGLISH corpus and related tasks for distant-speech recognition in domestic environments

Ravanelli

Cristoforetti

Gretter

et al. 2015

2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)

Self Cite

View full text Add to dashboard Cite

show abstract

“…For clarity, we entirely focus in this article on the compensation rules while ignoring the parameter estimation step. We also disregard approaches that apply a modified training method to conventional HMMs without exhibiting a distinct compensation step, as it is characteristic for, e.g., discriminative [28], multi-condition [29], or reverberant training [30].…”

Section: The Bayesian Viewmentioning

confidence: 99%

“…to y n . On the other hand, the modified MAP approximation (29) leads to a scaled version of the exact likelihood p(y n |q n ), cf. (27), with the scaling factor p(x MAP n |y n , q n ) being all the higher with increasing accuracy of the approximation (29).…”

Section: Remosmentioning

confidence: 99%

A Bayesian view on acoustic model-based techniques for robust speech recognition

Maas

Huemmer

Sehr

et al. 2015

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

This article provides a unifying Bayesian view on various approaches for acoustic model adaptation, missing feature, and uncertainty decoding that are well-known in the literature of robust automatic speech recognition. The representatives of these classes can often be deduced from a Bayesian network that extends the conventional hidden Markov models used in speech recognition. These extensions, in turn, can in many cases be motivated from an underlying observation model that relates clean and distorted feature vectors. By identifying and converting the observation models into a Bayesian network representation, we formulate the corresponding compensation rules. We thus summarize the various approaches as approximations or modifications of the same Bayesian decoding rule leading to a unified view on known derivations as well as to new formulations for certain approaches.

show abstract

“…environment prevents this form of matched reverberant training from being widely used in real-world applications. Synthetically generating the training data as suggested by [3,4] instead of recording them significantly reduces the effort for matched training. In this case, only the Room Impulse Response (RIR) of the target room needs to be measured or estimated, and then, a set of reverberant training data can be generated by convolving clean-speech signals with this RIR.…”

Section: Introductionmentioning

confidence: 99%

Multi-style training of HMMS with stereo data for reverberation-robust speech recognition

Sehr

Hofmann

Maas

et al. 2011

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

View full text Add to dashboard Cite

A novel training algorithm using data pairs of clean and reverberant feature vectors for estimating robust Hidden Markov Models (HMMs), introduced in [1] for matched training, is employed in this paper for multi-style training. The multi-style HMMs are derived from well-trained cleanspeech HMMs by aligning the clean data to the clean-speech HMM and using the resulting state-frame alignment to estimate the Gaussian mixture densities from the reverberant data of several different rooms. Thus, the temporal alignment is fixed for all reverberation conditions contained in the multi-style training set so that the model mismatch between the different rooms is reduced. Therefore, this training approach is particularly suitable for multi-style training. Multi-style HMMs trained by the proposed approach and adapted to the current room condition using maximum likelihood linear regression significantly outperform the corresponding adapted multi-style HMMs trained by the conventional Baum-Welch algorithm. In strongly reverberant rooms, the proposed adapted multi-style HMMs even outperform Baum-Welch HMMs trained on matched data.

show abstract

Hidden Markov model training with contaminated speech material for distant-talking speech recognition

Cited by 32 publications

References 41 publications

The DIRHA-ENGLISH corpus and related tasks for distant-speech recognition in domestic environments

The DIRHA-ENGLISH corpus and related tasks for distant-speech recognition in domestic environments

A Bayesian view on acoustic model-based techniques for robust speech recognition

Multi-style training of HMMS with stereo data for reverberation-robust speech recognition

Contact Info

Product

Resources

About