Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909241729613824 |
|---|---|
| author | Bataev, Vladimir Korostik, Roman Shabalin, Evgeny Lavrukhin, Vitaly Ginsburg, Boris |
| author_facet | Bataev, Vladimir Korostik, Roman Shabalin, Evgeny Lavrukhin, Vitaly Ginsburg, Boris |
| contents | We propose an end-to-end Automatic Speech Recognition (ASR) system that can be trained on transcribed speech data, text-only data, or a mixture of both. The proposed model uses an integrated auxiliary block for text-based training. This block combines a non-autoregressive multi-speaker text-to-mel-spectrogram generator with a GAN-based enhancer to improve the spectrogram quality. The proposed system can generate a mel-spectrogram dynamically during training. It can be used to adapt the ASR model to a new domain by using text-only data from this domain. We demonstrate that the proposed training method significantly improves ASR accuracy compared to the system trained on transcribed speech only. It also surpasses cascade TTS systems with the vocoder in the adaptation quality and training speed. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2302_14036 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator Bataev, Vladimir Korostik, Roman Shabalin, Evgeny Lavrukhin, Vitaly Ginsburg, Boris Audio and Speech Processing Computation and Language Machine Learning Sound We propose an end-to-end Automatic Speech Recognition (ASR) system that can be trained on transcribed speech data, text-only data, or a mixture of both. The proposed model uses an integrated auxiliary block for text-based training. This block combines a non-autoregressive multi-speaker text-to-mel-spectrogram generator with a GAN-based enhancer to improve the spectrogram quality. The proposed system can generate a mel-spectrogram dynamically during training. It can be used to adapt the ASR model to a new domain by using text-only data from this domain. We demonstrate that the proposed training method significantly improves ASR accuracy compared to the system trained on transcribed speech only. It also surpasses cascade TTS systems with the vocoder in the adaptation quality and training speed. |
| title | Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator |
| topic | Audio and Speech Processing Computation and Language Machine Learning Sound |
| url | https://arxiv.org/abs/2302.14036 |