An Exhaustive Evaluation of TTS- and VC-based Data Augmentation for ASR
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910870480617472 |
|---|---|
| author | Ogun, Sewade Colotte, Vincent Vincent, Emmanuel |
| author_facet | Ogun, Sewade Colotte, Vincent Vincent, Emmanuel |
| contents | Augmenting the training data of automatic speech recognition (ASR) systems with synthetic data generated by text-to-speech (TTS) or voice conversion (VC) has gained popularity in recent years. Several works have demonstrated improvements in ASR performance using this augmentation approach. However, because of the lower diversity of synthetic speech, naively combining synthetic and real data often does not yield the best results. In this work, we leverage recently proposed flow-based TTS/VC models allowing greater speech diversity, and assess the respective impact of augmenting various speech attributes on the word error rate (WER) achieved by several ASR models. Pitch augmentation and VC-based speaker augmentation are found to be ineffective in our setup. Jointly augmenting all other attributes reduces the WER of a Conformer-Transducer model by 11\% relative on Common Voice and by up to 35\% relative on LibriSpeech compared to training on real data only. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_08954 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An Exhaustive Evaluation of TTS- and VC-based Data Augmentation for ASR Ogun, Sewade Colotte, Vincent Vincent, Emmanuel Audio and Speech Processing Computation and Language Augmenting the training data of automatic speech recognition (ASR) systems with synthetic data generated by text-to-speech (TTS) or voice conversion (VC) has gained popularity in recent years. Several works have demonstrated improvements in ASR performance using this augmentation approach. However, because of the lower diversity of synthetic speech, naively combining synthetic and real data often does not yield the best results. In this work, we leverage recently proposed flow-based TTS/VC models allowing greater speech diversity, and assess the respective impact of augmenting various speech attributes on the word error rate (WER) achieved by several ASR models. Pitch augmentation and VC-based speaker augmentation are found to be ineffective in our setup. Jointly augmenting all other attributes reduces the WER of a Conformer-Transducer model by 11\% relative on Common Voice and by up to 35\% relative on LibriSpeech compared to training on real data only. |
| title | An Exhaustive Evaluation of TTS- and VC-based Data Augmentation for ASR |
| topic | Audio and Speech Processing Computation and Language |
| url | https://arxiv.org/abs/2503.08954 |