The JHU ASR System for VOiCES from a Distance Challenge 2019

This paper describes the system developed by the JHU team for automatic speech recognition (ASR) of the VOiCES from a Distance Challenge 2019, focusing on single channel distant/farfield audio under noisy conditions. We participated in the Fixed Condition track, where the systems are only trained on an 80hour subset of the Librispeech corpus provided by the organizer. The training data was first augmented with both background noises and simulated reverberation. We then trained factorized TDNN acoustic models that differed only in their use of i-vectors for adaptation. Both systems utilized RNN language models trained on original and reversed text for rescoring. We submitted three systems: the system using i-vectors with WER 19.4% on the development set, the system without i-vectors that achieved WER 19.0%, and the their lattice-level fusion with WER 17.8%. On the evaluation set, our best system achieves 23.9% WER.

[1]  Liang Lu,et al.  Deep beamforming networks for multi-channel speech recognition , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[2]  Yifan Gong,et al.  An Overview of Noise-Robust Automatic Speech Recognition , 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[3]  Sanjeev Khudanpur,et al.  Audio augmentation for speech recognition , 2015, INTERSPEECH.

[4]  Haihua Xu,et al.  Minimum Bayes Risk decoding and system combination based on a recursion for edit distance , 2011, Comput. Speech Lang..

[5]  Yiming Wang,et al.  Purely Sequence-Trained Neural Networks for ASR Based on Lattice-Free MMI , 2016, INTERSPEECH.

[6]  Yiming Wang,et al.  A Pruned Rnnlm Lattice-Rescoring Algorithm for Automatic Speech Recognition , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[7]  Tomohiro Nakatani,et al.  Making Machines Understand Us in Reverberant Rooms: Robustness Against Reverberation for Automatic Speech Recognition , 2012, IEEE Signal Processing Magazine.

[8]  Hans-Günter Hirsch,et al.  A new approach for the adaptation of HMMs to reverberation and background noise , 2008, Speech Commun..

[9]  Sanjeev Khudanpur,et al.  Pronunciation and silence probability modeling for ASR , 2015, INTERSPEECH.

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

[11]  Colleen Richey,et al.  The VOiCES from a Distance Challenge 2019 Evaluation Plan , 2019, ArXiv.

[12]  Sanjeev Khudanpur,et al.  A study on data augmentation of reverberant speech for robust speech recognition , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[13]  Li Lee,et al.  A frequency warping approach to speaker normalization , 1998, IEEE Trans. Speech Audio Process..

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

[15]  Richard M. Stern,et al.  A vector Taylor series approach for environment-independent speech recognition , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[16]  Longbiao Wang,et al.  Single-channel Dereverberation for Distant-Talking Speech Recognition by Combining Denoising Autoencoder and Temporal Structure Normalization , 2014, The 9th International Symposium on Chinese Spoken Language Processing.

[17]  Yiming Wang,et al.  Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks , 2018, INTERSPEECH.

[18]  R. Maas,et al.  A summary of the REVERB challenge: state-of-the-art and remaining challenges in reverberant speech processing research , 2016, EURASIP Journal on Advances in Signal Processing.

[19]  Longbiao Wang,et al.  Joint sparse representation based cepstral-domain dereverberation for distant-talking speech recognition , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[20]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Jian Wang,et al.  Neural Network Language Modeling with Letter-Based Features and Importance Sampling , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[22]  Philip C. Woodland,et al.  Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models , 1995, Comput. Speech Lang..

[23]  Jon Barker,et al.  The fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselines , 2018, INTERSPEECH.

[24]  Sanjeev Khudanpur,et al.  Librispeech: An ASR corpus based on public domain audio books , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[25]  Ulpu Remes,et al.  Techniques for Noise Robustness in Automatic Speech Recognition , 2012 .

[26]  Richard M. Stern,et al.  Efficient Cepstral Normalization for Robust Speech Recognition , 1993, HLT.

[27]  Longbiao Wang,et al.  Dereverberation and denoising based on generalized spectral subtraction by multi-channel LMS algorithm using a small-scale microphone array , 2012, EURASIP Journal on Advances in Signal Processing.

[28]  Florin Curelaru,et al.  Front-End Factor Analysis For Speaker Verification , 2018, 2018 International Conference on Communications (COMM).

[29]  Daniel Povey,et al.  MUSAN: A Music, Speech, and Noise Corpus , 2015, ArXiv.

[30]  George Saon,et al.  Speaker adaptation of neural network acoustic models using i-vectors , 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

[31]  Colleen Richey,et al.  Voices Obscured in Complex Environmental Settings (VOICES) corpus , 2018, INTERSPEECH.

[32]  Roland Maas,et al.  Model-based dereverberation in the logmelspec domain for robust distant-talking speech recognition , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[33]  Marc Delcroix,et al.  Precise Dereverberation Using Multichannel Linear Prediction , 2007, IEEE Transactions on Audio, Speech, and Language Processing.