To Reverse the Gradient or Not: an Empirical Comparison of Adversarial and Multi-task Learning in Speech Recognition
暂无分享,去创建一个
Nicolas Usunier | Neil Zeghidour | Gabriel Synnaeve | Ronan Collobert | Yossi Adi | Vitaliy Liptchinsky
[1] Jürgen Schmidhuber,et al. Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks , 2006, ICML.
[2] Biing-Hwang Juang,et al. Speaker-Invariant Training Via Adversarial Learning , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
[3] Mei-Yuh Hwang,et al. Domain Adversarial Training for Accented Speech Recognition , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
[4] Yonatan Belinkov,et al. Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks , 2016, ICLR.
[5] Thierry Dutoit,et al. Speaker-aware long short-term memory multi-task learning for speech recognition , 2016, 2016 24th European Signal Processing Conference (EUSIPCO).
[6] Sanjeev Khudanpur,et al. Reverberation robust acoustic modeling using i-vectors with time delay neural networks , 2015, INTERSPEECH.
[7] Sanjeev Khudanpur,et al. A time delay neural network architecture for efficient modeling of long temporal contexts , 2015, INTERSPEECH.
[8] Dimitri Palaz,et al. Jointly Learning to Locate and Classify Words Using Convolutional Networks , 2016, INTERSPEECH.
[9] Andrew W. Senior,et al. Improving DNN speaker independence with I-vector inputs , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
[10] Hermann Ney,et al. Improvements in beam search , 1994, ICSLP.
[11] Janet M. Baker,et al. The Design for the Wall Street Journal-based CSR Corpus , 1992, HLT.
[12] William Chan,et al. Deep Recurrent Neural Networks for Acoustic Modelling , 2015, ArXiv.
[13] François Laviolette,et al. Domain-Adversarial Training of Neural Networks , 2015, J. Mach. Learn. Res..
[14] Philipp Koehn,et al. Scalable Modified Kneser-Ney Language Model Estimation , 2013, ACL.
[15] Chong Wang,et al. Deep Speech 2 : End-to-End Speech Recognition in English and Mandarin , 2015, ICML.
[16] Bhaskar Mitra,et al. Cross Domain Regularization for Neural Ranking Models using Adversarial Learning , 2018, SIGIR.
[17] Dong Wang,et al. Multi-task recurrent model for speech and speaker recognition , 2016, 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA).
[18] Guillaume Lample,et al. Fader Networks: Manipulating Images by Sliding Attributes , 2017, NIPS.
[19] Rich Caruana,et al. Multitask Learning , 1997, Machine-mediated learning.
[20] Thierry Dutoit,et al. Multi-task learning for speech recognition: an overview , 2016, ESANN.
[21] Bhuvana Ramabhadran,et al. Invariant Representations for Noisy Speech Recognition , 2016, ArXiv.
[22] Sebastian Ruder,et al. An Overview of Multi-Task Learning in Deep Neural Networks , 2017, ArXiv.
[23] Xiaodong Cui,et al. English Conversational Telephone Speech Recognition by Humans and Machines , 2017, INTERSPEECH.
[24] Tetsuji Ogawa,et al. Speaker Invariant Feature Extraction for Zero-Resource Languages with Adversarial Learning , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
[25] 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).
[26] Frédéric Jurie,et al. An Adversarial Regularisation for Semi-Supervised Training of Structured Output Neural Networks , 2017, NIPS 2017.
[27] Yann Dauphin,et al. Language Modeling with Gated Convolutional Networks , 2016, ICML.
[28] Jason Weston,et al. Natural Language Processing (Almost) from Scratch , 2011, J. Mach. Learn. Res..
[29] Gabriel Synnaeve,et al. Wav2Letter: an End-to-End ConvNet-based Speech Recognition System , 2016, ArXiv.
[30] Tim Salimans,et al. Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks , 2016, NIPS.
[31] Yonatan Belinkov,et al. Analysis of sentence embedding models using prediction tasks in natural language processing , 2017, IBM J. Res. Dev..
[32] Gabriel Synnaeve,et al. Letter-Based Speech Recognition with Gated ConvNets , 2017, ArXiv.