Pushing the Limits of Non-Autoregressive Speech Recognition
arXiv:2104.03416 · doi:10.21437/Interspeech.2021-337
Abstract
We combine recent advancements in end-to-end speech recognition to non-autoregressive automatic speech recognition. We push the limits of non-autoregressive state-of-the-art results for multiple datasets: LibriSpeech, Fisher+Switchboard and Wall Street Journal. Key to our recipe, we leverage CTC on giant Conformer neural network architectures with SpecAugment and wav2vec2 pre-training. We achieve 1.8%/3.6% WER on LibriSpeech test/test-other sets, 5.1%/9.8% WER on Switchboard, and 3.4% on the Wall Street Journal, all without a language model.
arXiv commentProceedings of INTERSPEECH
References in corpus (14)
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
- Language Models are Few-Shot Learners
- Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
- Squeeze-and-Excitation Networks
- Big Self-Supervised Models are Strong Semi-Supervised Learners
- Libri-Light: A Benchmark for ASR with Limited or No Supervision
- Conformer: Convolution-augmented Transformer for Speech Recognition
- Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition
- Fully Convolutional Speech Recognition
- ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context
- Exploring Neural Transducers for End-to-End Speech Recognition
- Imputer: Sequence Modelling via Imputation and Dynamic Programming
- An investigation of phone-based subword units for end-to-end speech recognition
- Improved Mask-CTC for Non-Autoregressive End-to-End ASR
Cited by in corpus (5)
- A CTC Alignment-based Non-autoregressive Transformer for End-to-end Automatic Speech Recognition
- Non-autoregressive Transformer-based End-to-end ASR using BERT
- PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition
- UniEnc-CASSNAT: An Encoder-only Non-autoregressive ASR for Speech SSL Models
- Fast-MD: Fast Multi-Decoder End-to-End Speech Translation with Non-Autoregressive Hidden Intermediates