Single and multi-channel approaches for distant speech recognition under noisy reverberant conditions: I2R'S system description for the ASpIRE challenge

In this paper, we introduce the system developed at the Institute for Infocomm Research (I2 R) for the ASpIRE (Automatic Speech recognition In Reverberant Environments) challenge. The main components of the system are a front-end processing system consisting of a distributed beam-forming algorithm, that performs adaptive weighting and channel elimination, a speech dereverberation approach using a maximum-kurtosis criteria, and a robust voice activity detection (VAD) module based on using the sub-harmonic ratio (SHR). The acoustic back-end consists of a multi-conditional Deep Neural Network (DNN) model that uses speaker adapted features combined with a decoding strategy that performs semi-supervised DNN model adaptation using weighted labels generated by the first-pass decoding output. On the single-microphone evaluation, our system achieved a word error rate (WER) of 44.8%. With the incorporation of beamforming on the multi-microphone evaluation, our system achieved an improvement in WER of over 6% to give the best evaluation result of 38.5%.

[1]  Vysoké Učení,et al.  Statistical Language Models Based on Neural Networks , 2012 .

[2]  Shinji Watanabe,et al.  Discriminative training based on an integrated view of MPE and MMI in margin and error space , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[3]  Lukás Burget,et al.  Semi-supervised training of Deep Neural Networks , 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

[4]  Xuejing Sun,et al.  Pitch determination and voice quality analysis using Subharmonic-to-Harmonic Ratio , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[5]  Mary Harper.  The Automatic Speech recogition In Reverberant Environments (ASpIRE) challenge , 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

[6]  G. Carter,et al.  The generalized correlation method for estimation of time delay , 1976 .

[7]  Zhengyou Zhang,et al.  Why does PHAT work well in lownoise, reverberative environments? , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[8]  Daniel Povey,et al.  The Kaldi Speech Recognition Toolkit , 2011 .

[9]  F. Itakura,et al.  Robust SNR estimation of noisy speech based on Gaussian mixture modeling on log-power domain , 2004 .

[10]  Xavier Anguera Miró,et al.  Acoustic Beamforming for Speaker Diarization of Meetings , 2007, IEEE Transactions on Audio, Speech, and Language Processing.

[11]  Henrique S. Malvar,et al.  Speech dereverberation via maximum-kurtosis subband adaptive filtering , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

[12]  David Miller,et al.  The Fisher Corpus: a Resource for the Next Generations of Speech-to-Text , 2004, LREC.

[13]  Hank Liao,et al.  Speaker adaptation of context dependent deep neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[14]  Vikrant Singh Tomar.  Blind Dereverberation using Maximum Kurtosis of the Speech Residual , 2010 .

[15]  Yong Rui,et al.  Time delay estimation in the presence of correlated noise and reverberation , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[16]  Lukás Burget,et al.  Sequence-discriminative training of deep neural networks , 2013, INTERSPEECH.

[17]  Abeer Alwan,et al.  Joint Robust Voicing Detection and Pitch Estimation Based on Residual Harmonics , 2019, INTERSPEECH.