Word Order Does Not Matter For Speech Recognition
Not on the map. Why?
Abstract (arXiv)
In this paper, we study training of automatic speech recognition system in a weakly supervised setting where the order of words in transcript labels of the audio training data is not known. We train a word-level acoustic model which aggregates the distribution of all output frames using LogSumExp operation and uses a cross-entropy loss to match with the ground-truth words distribution. Using the pseudo-labels generated from this model on the training set, we then train a letter-based acoustic model using Connectionist Temporal Classification loss. Our system achieves 2.3%/4.6% on test-clean/test-other subsets of LibriSpeech, which closely matches with the supervised baseline's performance.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 29 of its 36 references that are in the map. First posted on arXiv 12 Oct 2021.
Builds on
29 of 36 references.
References · 29
- 2017Attention Is All You Needcited by 59,932
- 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
- 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
- 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
- 2019Reducing Transformer Depth on Demand with Structured Dropoutcited by 434
- 2020TERA: Self-Supervised Learning of Transformer Encoder Representation for Speechcited by 186
- 2019An Unsupervised Autoregressive Model for Speech Representation Learningcited by 185
- 2020Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognitioncited by 185
- 2021Unsupervised Speech Recognitioncited by 147
- 2020Improved Noisy Student Training for Automatic Speech Recognitioncited by 139
- 2019Self-Training for End-to-End Speech Recognitioncited by 128
- 2020Multi-task self-supervised learning for Robust Speech Recognitioncited by 127
17 more
- 2019End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architecturescited by 120
- 2020Iterative Pseudo-Labeling for Speech Recognitioncited by 81
- 2020Rethinking Evaluation in ASR: Are Our Models Robust Enough?cited by 72
- 2020SlimIPL: Language-Model-Free Iterative Pseudo-Labelingcited by 54
- 2020Non-Autoregressive Predictive Coding for Learning Speech Representations from Local Dependenciescited by 47
- 2018wav2letter++: The Fastest Open-source Speech Recognition Systemcited by 42
- 2021Momentum Pseudo-Labeling for Semi-Supervised Speech Recognitioncited by 37
- 2020Semi-supervised ASR by End-to-end Self-trainingcited by 29
- 2021Wav2vec-C: A Self-supervised Model for Speech Representation Learningcited by 25
- 2018Completely Unsupervised Phoneme Recognition by Adversarially Learning Mapping Relationships from Audio Embeddingscited by 22
- 2018Unsupervised Speech Recognition via Segmental Empirical Output Distribution Matchingcited by 20
- 2020Joint Masked CPC and CTC Training for ASRcited by 20
- 2020Semi-Supervised Speech Recognition via Graph-based Temporal Classificationcited by 19
- 2017Visually grounded learning of keyword prediction from untranscribed speechcited by 16
- 2019Acoustically Grounded Word Embeddings for Improved Acoustics-to-Word Speech Recognitioncited by 15
- 2019Completely Unsupervised Speech Recognition By A Generative Adversarial Network Harmonized With Iteratively Refined Hidden Markov Modelscited by 8
- 2020Large scale weakly and semi-supervised learning for low-resource video ASRcited by 7
Built on by
Citing papers per year: 2022: 2.
2 papers.