mlsanityData to 7 Oct 2026

Non-Parallel Voice Conversion for ASR Augmentation

arXiv 2209.06987 ↗First posted 15 Sep 2022cs.SD cs.LG eess.AScited by 2

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 17 of its 30 references that are in the map. First posted on arXiv 15 Sep 2022.

Builds on

17 of 30 references.

References · 17

  1. 2017Neural Discrete Representation Learningcited by 4,650
  2. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  3. 2019AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Losscited by 189
  4. 2020The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modelingcited by 100
  5. 2020Unsupervised Speech Decomposition via Triple Information Bottleneckcited by 87
  6. 2020Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modelingcited by 65
  7. 2020Vector-quantized neural networks for acoustic unit discovery in the ZeroSpeech 2020 challengecited by 55
  8. 2016Voice Conversion from Non-parallel Corpora Using Variational Auto-encodercited by 45
  9. 2021Injecting Text in Self-Supervised Speech Pretrainingcited by 24
  10. 2019Non-Parallel Sequence-to-Sequence Voice Conversion with Disentangled Linguistic and Speaker Representationscited by 23
  11. 2019Non-Parallel Voice Conversion with Cyclic Variational Autoencodercited by 15
  12. 2020Accent and Speaker Disentanglement in Many-to-many Voice Conversioncited by 15
5 more
  1. 2020Unsupervised Representation Disentanglement using Cross Domain Features and Adversarial Learning in Variational Autoencoder based Voice Conversioncited by 13
  2. 2021Voice Conversion Can Improve ASR in Very Low-Resource Settingscited by 13
  3. 2021crank: An Open-Source Software for Nonparallel Voice Conversion Based on Vector-Quantized Variational Autoencodercited by 6
  4. 2020The NeteaseGames System for Voice Conversion Challenge 2020 with Vector-quantization Variational Autoencoder and WaveNetcited by 2
  5. 2021Enriching Source Style Transfer in Recognition-Synthesis based Non-Parallel Voice Conversioncited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 0; 2025: 0; 2026: 1.

2 papers.

  1. 2023Iteratively Improving Speech Recognition and Voice Conversioncited by 1
  2. 2026Synthetic Audio Generation Framework for Air Traffic Control Speech Recognitioncited by 0