Spoken Language Corpora Augmentation with Domain-Specific Voice-Cloned Speech
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917918150754304 |
|---|---|
| author | Czyżnikiewicz, Mateusz Bondaruk, Łukasz Kubiak, Jakub Wiącek, Adam Degórski, Łukasz Kubis, Marek Skórzewski, Paweł |
| author_facet | Czyżnikiewicz, Mateusz Bondaruk, Łukasz Kubiak, Jakub Wiącek, Adam Degórski, Łukasz Kubis, Marek Skórzewski, Paweł |
| contents | In this paper we study the impact of augmenting spoken language corpora with domain-specific synthetic samples for the purpose of training a speech recognition system. Using both a conventional neural TTS system and a zero-shot one with voice cloning ability we generate speech corpora that vary in the number of voices. We compare speech recognition models trained with addition of different amounts of synthetic data generated using these two methods with a baseline model trained solely on voice recordings. We show that while the quality of voice-cloned dataset is lower, its increased multivoiceity makes it much more effective than the one with only a few voices synthesized with the use of a conventional neural TTS system. Furthermore, our experiments indicate that using low variability synthetic speech quickly leads to saturation in the quality of the ASR whereas high variability speech provides improvement even when increasing total amount of data used for training by 30%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_07090 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Spoken Language Corpora Augmentation with Domain-Specific Voice-Cloned Speech Czyżnikiewicz, Mateusz Bondaruk, Łukasz Kubiak, Jakub Wiącek, Adam Degórski, Łukasz Kubis, Marek Skórzewski, Paweł Audio and Speech Processing In this paper we study the impact of augmenting spoken language corpora with domain-specific synthetic samples for the purpose of training a speech recognition system. Using both a conventional neural TTS system and a zero-shot one with voice cloning ability we generate speech corpora that vary in the number of voices. We compare speech recognition models trained with addition of different amounts of synthetic data generated using these two methods with a baseline model trained solely on voice recordings. We show that while the quality of voice-cloned dataset is lower, its increased multivoiceity makes it much more effective than the one with only a few voices synthesized with the use of a conventional neural TTS system. Furthermore, our experiments indicate that using low variability synthetic speech quickly leads to saturation in the quality of the ASR whereas high variability speech provides improvement even when increasing total amount of data used for training by 30%. |
| title | Spoken Language Corpora Augmentation with Domain-Specific Voice-Cloned Speech |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2406.07090 |