Snri Target Training For Joint Speech Enhancement And Recognition
2021 · Yuma Koizumi, Shigeki Karita, Arun Narayanan, et al.
Abstract
Speech enhancement (SE) is used as a frontend in speech applications including automatic speech recognition (ASR) and telecommunication. A difficulty in using the SE frontend is that the appropriate noise reduction level differs depending on applications and/or noise characteristics. In this study, we propose "signal-to-noise ratio improvement (SNRi) target training"; the SE frontend is trained to output a signal whose SNRi is controlled by an auxiliary scalar input. In joint training with a backend, the target SNRi value is estimated by an auxiliary network. By training all networks to minimize the backend task loss, we can estimate the appropriate noise reduction level for each noisy input in a data-driven scheme. Our experiments showed that the SNRi target training enables control of the output SNRi. In addition, the proposed joint training relatively reduces word error rate by 4.0% and 5.7% compared to a Conformer-based standard ASR model and conventional SE-ASR joint training mode
Authors
(none)
Tags
Stats
Related papers
- Joint Training Of Speech Enhancement And Self-supervised Model For Noise-robust ASR (2022)0.00
- How Does End-to-end Speech Recognition Training Impact Speech Enhancement Artifacts? (2023)7.50
- Bridging The Gap: Integrating Pre-trained Speech Enhancement And Recognition Models For Robust Speech Recognition (2024)7.50
- Reinforcement Learning Based Speech Enhancement For Robust Speech Recognition (2018)11.08
- Human Listening And Live Captioning: Multi-task Training For Speech Enhancement (2021)9.92
- A Conformer-based ASR Frontend For Joint Acoustic Echo Cancellation, Speech Enhancement And Speech Separation (2021)9.23
- Towards Decoupling Frontend Enhancement And Backend Recognition In Monaural Robust ASR (2024)4.52
- Speech And Noise Dual-stream Spectrogram Refine Network With Speech Distortion Loss For Robust Speech Recognition (2023)5.24