Abstract
Automatic speech recognition (ASR) needs to be robust to speaker differences. Voice Conversion (VC) modifies speaker characteristics of input speech. This is an attractive feature for ASR data augmentation. In this paper, we demonstrate that voice conversion can be used as a data augmentation technique to improve ASR performance, even on LibriSpeech, which contains 2, 456 speakers. For ASR augmentation, it is necessary that the VC model be robust to a wide range of input speech. This motivates the use of a non-autoregressive, non-parallel VC model, and the use of a pretrained ASR encoder within the VC model. This work suggests that despite including many speakers, speaker diversity may remain a limitation to ASR quality. Finally, interrogation of our VC performance has provided useful metrics for objective evaluation of VC quality.
| Original language | English |
|---|---|
| Pages (from-to) | 3408-3412 |
| Number of pages | 5 |
| Journal | Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH |
| Volume | 2022-September |
| DOIs | |
| State | Published - 1 Jan 2022 |
| Externally published | Yes |
| Event | 23rd Annual Conference of the International Speech Communication Association, INTERSPEECH 2022 - Incheon, Korea, Republic of Duration: 18 Sep 2022 → 22 Sep 2022 |
Keywords
- Automatic Speech Recognition
- Voice Conversion
ASJC Scopus subject areas
- Software
- Signal Processing
- Language and Linguistics
- Modeling and Simulation
- Human-Computer Interaction
Fingerprint
Dive into the research topics of 'Non-Parallel Voice Conversion for ASR Augmentation'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver