Towards Better Decoding and Language Model Integration in Sequence to Sequence Models

The recently proposed Sequence-to-Sequence (seq2seq) framework advocates replacing complex data processing pipelines, such as an entire automatic speech recognition system, with a single neural network trained in an end-to-end fashion. In this contribution, we analyse an attention-based seq2seq speech recognition system that directly transcribes recordings into characters. We observe two shortcomings: overconfidence in its predictions and a tendency to produce incomplete transcriptions when language models are used. We propose practical solutions to both problems achieving competitive speaker independent word error rates on the Wall Street Journal dataset: without separate language models we reach 10.6% WER, while together with a trigram language model, we reach 6.7% WER.

[1]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[2]  Wu Chou,et al.  Discriminative learning in sequential pattern recognition , 2008, IEEE Signal Processing Magazine.

[3]  Chong Wang,et al.  Deep Speech 2 : End-to-End Speech Recognition in English and Mandarin , 2015, ICML.

[4]  Quoc V. Le,et al.  Listen, Attend and Spell , 2015, ArXiv.

[5]  Alex Graves,et al.  Asynchronous Methods for Deep Reinforcement Learning , 2016, ICML.

[6]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[7]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[8]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Yu Zhang,et al.  Very deep convolutional networks for end-to-end speech recognition , 2016, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[10]  Slav Petrov,et al.  Globally Normalized Transition-Based Neural Networks , 2016, ACL.

[11]  Zhiguo Wang,et al.  A Coverage Embedding Model for Neural Machine Translation , 2016, ArXiv.

[12]  Yoshua Bengio,et al.  Attention-Based Models for Speech Recognition , 2015, NIPS.

[13]  Armen Aghajanyan.  SoftTarget Regularization: An Effective Technique to Reduce Over-Fitting in Neural Networks , 2017, 2017 3rd IEEE International Conference on Cybernetics (CYBCON).

[14]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

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

[16]  Yoshua Bengio,et al.  End-to-end attention-based large vocabulary speech recognition , 2015, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[17]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[18]  Christopher D. Manning,et al.  Effective Approaches to Attention-based Neural Machine Translation , 2015, EMNLP.

[19]  Johan Schalkwyk,et al.  OpenFst: A General and Efficient Weighted Finite-State Transducer Library , 2007, CIAA.

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

[21]  Qi Tian,et al.  DisturbLabel: Regularizing CNN on the Loss Layer , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups , 2012, IEEE Signal Processing Magazine.

[23]  Yu Zhang,et al.  Latent Sequence Decompositions , 2016, ICLR.

[24]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[25]  Geoffrey E. Hinton,et al.  Regularizing Neural Networks by Penalizing Confident Output Distributions , 2017, ICLR.

[26]  Yoshua Bengio,et al.  On Using Monolingual Corpora in Neural Machine Translation , 2015, ArXiv.

[27]  George Kurian,et al.  Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation , 2016, ArXiv.

[28]  Navdeep Jaitly,et al.  Learning online alignments with continuous rewards policy gradient , 2016, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[29]  Alexander M. Rush,et al.  Sequence-to-Sequence Learning as Beam-Search Optimization , 2016, EMNLP.

[30]  Joon Son Chung,et al.  Lip Reading Sentences in the Wild , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[31]  Jing Peng,et al.  Function Optimization using Connectionist Reinforcement Learning Algorithms , 1991 .

[32]  Yang Liu,et al.  Modeling Coverage for Neural Machine Translation , 2016, ACL.

[33]  Yajie Miao,et al.  EESEN: End-to-end speech recognition using deep RNN models and WFST-based decoding , 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

[34]  Navdeep Jaitly,et al.  Towards End-To-End Speech Recognition with Recurrent Neural Networks , 2014, ICML.