mlsanityData to 7 Oct 2026

Dual Learning for Large Vocabulary On-Device ASR

arXiv 2301.04327 ↗First posted 11 Jan 2023cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Dual learning is a paradigm for semi-supervised machine learning that seeks to leverage unsupervised data by solving two opposite tasks at once. In this scheme, each model is used to generate pseudo-labels for unlabeled examples that are used to train the other model. Dual learning has seen some use in speech processing by pairing ASR and TTS as dual tasks. However, these results mostly address only the case of using unpaired examples to compensate for very small supervised datasets, and mostly on large, non-streaming models. Dual learning has not yet been proven effective for using unsupervised data to improve realistic on-device streaming models that are already trained on large supervised corpora. We provide this missing piece though an analysis of an on-device-sized streaming conformer trained on the entirety of Librispeech, showing relative WER improvements of 10.7%/5.2% without an LM and 11.7%/16.4% with an LM.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 30 of its 38 references that are in the map. First posted on arXiv 11 Jan 2023.

Builds on

30 of 38 references.

References · 30

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  5. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  6. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,609
  7. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  8. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 800
  9. 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 779
  10. 2019Libri-Light: A Benchmark for ASR with Limited or No Supervisioncited by 462
  11. 2019vq-wav2vec: Self-Supervised Learning of Discrete Speech Representationscited by 335
  12. 2019Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoderscited by 196
18 more
  1. 2015On Using Monolingual Corpora in Neural Machine Translationcited by 149
  2. 2016Dual Learning for Machine Translationcited by 146
  3. 2020Hybrid Autoregressive Transducer (hat)cited by 106
  4. 2019Unsupervised speech representation learning using WaveNet autoencoderscited by 90
  5. 2017Cold Fusion: Training Seq2Seq Models Together with Language Modelscited by 87
  6. 2019Effectiveness of self-supervised pre-training for speech recognitioncited by 72
  7. 2020Vector-Quantized Autoregressive Predictive Codingcited by 69
  8. 2020Cascaded encoders for unifying streaming and non-streaming ASRcited by 51
  9. 2020Non-Autoregressive Predictive Coding for Learning Speech Representations from Local Dependenciescited by 47
  10. 2017Listening while Speaking: Speech Chain by Deep Learningcited by 46
  11. 2020LRSpeech: Extremely Low-Resource Speech Synthesis and Recognitioncited by 43
  12. 2019Almost Unsupervised Text to Speech and Automatic Speech Recognitioncited by 41
  13. 2021Tied & Reduced RNN-T Decodercited by 35
  14. 2018Cycle-consistency training for end-to-end speech recognitioncited by 31
  15. 2019Improving Transformer-based Speech Recognition Using Unsupervised Pre-trainingcited by 29
  16. 2020Improving Tail Performance of a Deliberation E2E ASR Model Using a Large Text Corpuscited by 24
  17. 2021Injecting Text in Self-Supervised Speech Pretrainingcited by 24
  18. 2018Discrete Autoencoders for Sequence Modelscited by 23

Built on by

Not cited yet.