Far-Field ASR Without Parallel Data

In far-field speech recognition systems, training acoustic models with alignments generated from parallel close-talk microphone data provides significant improvements. However it is not practical to assume the availability of large corpora of parallel close-talk microphone data, for training. In this paper we explore methods to reduce the performance gap between far-field ASR systems trained with alignments from distant microphone data and those trained with alignments from parallel close-talk microphone data. These methods include the use of a lattice-free sequence objective function which tolerates minor mis-alignment errors; and the use of data selection techniques to discard badly aligned data. We present results on single distant microphone and multiple distant microphone scenarios of the AMI LVCSR task. We identify prominent causes of alignment errors in AMI data.

[1]  Jürgen Schmidhuber,et al.  Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks , 2006, ICML.

[2]  Thomas Hain,et al.  Recognition and interpretation of meetings: The AMI and AMIDA projects , 2007 .

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

[4]  Jean Carletta,et al.  The AMI meeting corpus , 2005 .

[5]  Xiaohui Zhang,et al.  Parallel training of Deep Neural Networks with Natural Gradient and Parameter Averaging , 2014, ICLR.

[6]  Andrew W. Senior,et al.  Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition , 2014, ArXiv.

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

[8]  Jonathan Le Roux,et al.  Discriminative Training for Large-Vocabulary Speech Recognition Using Minimum Classification Error , 2007, IEEE Transactions on Audio, Speech, and Language Processing.

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

[10]  Erich Elsen,et al.  Deep Speech: Scaling up end-to-end speech recognition , 2014, ArXiv.

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

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

[13]  Tara N. Sainath,et al.  Acoustic modelling with CD-CTC-SMBR LSTM RNNS , 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

[14]  Lukás Burget,et al.  The AMI Meeting Transcription System: Progress and Performance , 2006, MLMI.

[15]  Johan Schalkwyk,et al.  Learning acoustic frame labeling for speech recognition with recurrent neural networks , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[16]  Steve Renals,et al.  Hybrid acoustic models for distant and multichannel large vocabulary speech recognition , 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

[17]  Andrew W. Senior,et al.  Fast and accurate recurrent neural network acoustic models for speech recognition , 2015, INTERSPEECH.

[18]  Jean Carletta,et al.  The AMI Meeting Corpus: A Pre-announcement , 2005, MLMI.

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

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

[21]  Sanjeev Khudanpur,et al.  Reverberation robust acoustic modeling using i-vectors with time delay neural networks , 2015, INTERSPEECH.

[22]  Sanjeev Khudanpur,et al.  A time delay neural network architecture for efficient modeling of long temporal contexts , 2015, INTERSPEECH.