Combining Unsupervised and Text Augmented Semi-Supervised Learning for Low Resourced Autoregressive Speech Recognition
| Autor: | Chak-Fai Li, Francis Keith, William Hartmann, Matthew Snover |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Sound (cs.SD) Computer Science - Computation and Language Audio and Speech Processing (eess.AS) FOS: Electrical engineering electronic engineering information engineering Computation and Language (cs.CL) Computer Science - Sound Electrical Engineering and Systems Science - Audio and Speech Processing |
| Popis: | Recent advances in unsupervised representation learning have demonstrated the impact of pretraining on large amounts of read speech. We adapt these techniques for domain adaptation in low-resource -- both in terms of data and compute -- conversational and broadcast domains. Moving beyond CTC, we pretrain state-of-the-art Conformer models in an unsupervised manner. While the unsupervised approach outperforms traditional semi-supervised training, the techniques are complementary. Combining the techniques is a 5% absolute improvement in WER, averaged over all conditions, compared to semi-supervised training alone. Additional text data is incorporated through external language models. By using CTC-based decoding, we are better able to take advantage of the additional text data. When used as a transcription model, it allows the Conformer model to better incorporate the knowledge from the language model through semi-supervised training than shallow fusion. Final performance is an additional 2% better absolute when using CTC-based decoding for semi-supervised training compared to shallow fusion. 5 pages, minor changes for camera ready version, to be published in IEEE ICASSP 2022 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|