mlsanityData to 19 Oct 2026

Enhancing Speech Recognition through Text-to-Speech and Voice Conversion Augmentation

arXiv 2610.13662 ↗First posted 9 Oct 2026cs.SD eess.AScited by 0

On the map: Speech and audio language models → ASR evaluation, bias and atypical speech

Abstract (arXiv)

Given the challenges associated with obtaining large volumes of real-world audio, the advancement of Automatic Speech Recognition (ASR) systems increasingly depends on synthetic data. This study focuses on the call center-banking domain, providing a targeted analysis of ASR models in this context. We evaluate real and synthetic datasets, using Word Error Rate (WER) and Character Error Rate (CER) as metrics, and employ a speech quality model to assess the impact on ASR performance. Our research compares Text-to-Speech (TTS) and advanced voice conversion methods, including KNNVC, Seed-VC, and Vec2Wav2, revealing significant improvements in speech quality and ASR accuracy, particularly with Seed-VC. Additionally, our domain-specific experimentation provides insight into the unique challenges and opportunities that arise when applying ASR technologies to industry-relevant settings. This highlights the potential of voice conversion technologies to enhance ASR systems, guiding future research in diverse linguistic scenarios, and paving the way for the broader application of ASR innovations across various fields.

Key facts. No citing papers in the map yet (data through 19 Oct 2026). Placed in ASR evaluation, bias and atypical speech, one of 11 directions in Speech and audio language models. Builds on 20 of its 23 references that are in the map. First posted on arXiv 9 Oct 2026.

Builds on

20 of 23 references.

References · 20

  1. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 2,293
  2. 2016WaveNet: A Generative Model for Raw Audiocited by 1,880
  3. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,596
  4. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,462
  5. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 1,023
  6. 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 1,007
  7. 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 947
  8. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 737
  9. 2018Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesiscited by 352
  10. 2021NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasetscited by 270
  11. 2023Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervisioncited by 232
  12. 2019AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Losscited by 224
8 more
  1. 2023Zipformer: A faster and better encoder for automatic speech recognitioncited by 112
  2. 2023Voice Conversion With Just Nearest Neighborscited by 78
  3. 2024Zero-shot Voice Conversion with Diffusion Transformerscited by 57
  4. 2018Training Neural Speech Recognition Systems with Synthetic Speech Augmentationcited by 23
  5. 2021Voice Conversion Can Improve ASR in Very Low-Resource Settingscited by 17
  6. 2022ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversioncited by 15
  7. 2024vec2wav 2.0: Advancing Voice Conversion via Discrete Token Vocoderscited by 7
  8. 2025An Exhaustive Evaluation of TTS- and VC-based Data Augmentation for ASRcited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026An Analysis of the Effectiveness of Synthetic Speech Data for ASR Fine-tuning in Selected Indic Languages
  2. 2026Phoneme-guided TTS augmentation for ASR: A unified pipeline and multilingual evaluation
  3. 2023Text Generation with Speech Synthesis for ASR Data Augmentation
  4. 2023Iteratively Improving Speech Recognition and Voice Conversion
  5. 2024Enhancing Low-Resource ASR through Versatile TTS: Bridging the Data Gap
  6. 2022Non-Parallel Voice Conversion for ASR Augmentation
  7. 2021Comparing the Benefit of Synthetic Training Data for Various Automatic Speech Recognition Architectures
  8. 2025Synthetic Voice Data for Automatic Speech Recognition in African Languages