# A Complementary Joint Training Approach Using Unpaired Speech and Text for Low-Resource Automatic Speech Recognition

arXiv: https://arxiv.org/abs/2204.02023 · HTML: https://mlsanity.com/paper/2204.02023/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 42 references that are in the map.
- First posted on arXiv 5 Apr 2022.

## Builds on (most cited first, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Self-Attention with Relative Position Representations](https://mlsanity.com/paper/1803.02155/) (2018)
- [Listen, Attend and Spell](https://mlsanity.com/paper/1508.01211/) (2015)
- [Libri-Light: A Benchmark for ASR with Limited or No Supervision](https://mlsanity.com/paper/1912.07875/) (2019)
- [Insights on representational similarity in neural networks with canonical correlation](https://mlsanity.com/paper/1806.05759/) (2018)
- [State-of-the-art Speech Recognition With Sequence-to-Sequence Models](https://mlsanity.com/paper/1712.01769/) (2017)
- [SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing](https://mlsanity.com/paper/2110.07205/) (2021)
- [An analysis of incorporating an external language model into a sequence-to-sequence model](https://mlsanity.com/paper/1712.01996/) (2017)
- [Towards better decoding and language model integration in sequence to sequence models](https://mlsanity.com/paper/1612.02695/) (2016)
- [Self-training and Pre-training are Complementary for Speech Recognition](https://mlsanity.com/paper/2010.11430/) (2020)
- [Cold Fusion: Training Seq2Seq Models Together with Language Models](https://mlsanity.com/paper/1708.06426/) (2017)
- [Iterative Pseudo-Labeling for Speech Recognition](https://mlsanity.com/paper/2005.09267/) (2020)
- [SlimIPL: Language-Model-Free Iterative Pseudo-Labeling](https://mlsanity.com/paper/2010.11524/) (2020)
- [Listening while Speaking: Speech Chain by Deep Learning](https://mlsanity.com/paper/1707.04879/) (2017)
- [Transformers with convolutional context for ASR](https://mlsanity.com/paper/1904.11660/) (2019)
- [Almost Unsupervised Text to Speech and Automatic Speech Recognition](https://mlsanity.com/paper/1905.06791/) (2019)
- [Very Deep Convolutional Networks for End-to-End Speech Recognition](https://mlsanity.com/paper/1610.03022/) (2016)
- [Cycle-consistency training for end-to-end speech recognition](https://mlsanity.com/paper/1811.01690/) (2018)
- [Multi-Modal Data Augmentation for End-to-End ASR](https://mlsanity.com/paper/1803.10299/) (2018)
- [Efficiently Fusing Pretrained Acoustic and Linguistic Encoders for Low-resource Speech Recognition](https://mlsanity.com/paper/2101.06699/) (2021)
- [Wav-BERT: Cooperative Acoustic and Linguistic Representation Learning for Low-Resource Speech Recognition](https://mlsanity.com/paper/2109.09161/) (2021)
- [Improving Hybrid CTC/Attention End-to-end Speech Recognition with Pretrained Acoustic and Language Model](https://mlsanity.com/paper/2112.07254/) (2021)
- [Unsupervised pre-training for sequence to sequence speech recognition](https://mlsanity.com/paper/1910.12418/) (2019)

## Built on by (most cited first, 1 of 1)

- [Master-ASR: Achieving Multilingual Scalability and Low-Resource Adaptation in ASR with Modular Learning](https://mlsanity.com/paper/2306.15686/) (2023)

## Abstract (arXiv)

Unpaired data has shown to be beneficial for low-resource automatic speech recognition~(ASR), which can be involved in the design of hybrid models with multi-task training or language model dependent pre-training. In this work, we leverage unpaired data to train a general sequence-to-sequence model. Unpaired speech and text are used in the form of data pairs by generating the corresponding missing parts in prior to model training. Inspired by the complementarity of speech-PseudoLabel pair and SynthesizedAudio-text pair in both acoustic features and linguistic features, we propose a complementary joint training~(CJT) method that trains a model alternatively with two data pairs. Furthermore, label masking for pseudo-labels and gradient restriction for synthesized audio are proposed to further cope with the deviations from real data, termed as CJT++. Experimental results show that compared to speech-only training, the proposed basic CJT achieves great performance improvements on clean/other test sets, and the CJT++ re-training yields further performance enhancements. It is also apparent that the proposed method outperforms the wav2vec2.0 model with the same model size and beam size, particularly in extreme low-resource cases.