Enhancing Kurdish Text-to-Speech with Native Corpus Training: A High-Quality WaveGlow Vocoder Approach
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929511913750528 |
|---|---|
| author | Abdullah, Abdulhady Abas Muhamad, Sabat Salih Veisi, Hadi |
| author_facet | Abdullah, Abdulhady Abas Muhamad, Sabat Salih Veisi, Hadi |
| contents | The ability to synthesize spoken language from text has greatly facilitated access to digital content with the advances in text-to-speech technology. However, effective TTS development for low-resource languages, such as Central Kurdish (CKB), still faces many challenges due mainly to the lack of linguistic information and dedicated resources. In this paper, we improve the Kurdish TTS system based on Tacotron by training the Kurdish WaveGlow vocoder on a 21-hour central Kurdish speech corpus instead of using a pre-trained English vocoder WaveGlow. Vocoder training on the target language corpus is required to accurately and fluently adapt phonetic and prosodic changes in Kurdish language. The effectiveness of these enhancements is that our model is significantly better than the baseline system with English pretrained models. In particular, our adaptive WaveGlow model achieves an impressive MOS of 4.91, which sets a new benchmark for Kurdish speech synthesis. On one hand, this study empowers the advanced features of the TTS system for Central Kurdish, and on the other hand, it opens the doors for other dialects in Kurdish and other related languages to further develop. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_13734 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing Kurdish Text-to-Speech with Native Corpus Training: A High-Quality WaveGlow Vocoder Approach Abdullah, Abdulhady Abas Muhamad, Sabat Salih Veisi, Hadi Computation and Language Sound Audio and Speech Processing The ability to synthesize spoken language from text has greatly facilitated access to digital content with the advances in text-to-speech technology. However, effective TTS development for low-resource languages, such as Central Kurdish (CKB), still faces many challenges due mainly to the lack of linguistic information and dedicated resources. In this paper, we improve the Kurdish TTS system based on Tacotron by training the Kurdish WaveGlow vocoder on a 21-hour central Kurdish speech corpus instead of using a pre-trained English vocoder WaveGlow. Vocoder training on the target language corpus is required to accurately and fluently adapt phonetic and prosodic changes in Kurdish language. The effectiveness of these enhancements is that our model is significantly better than the baseline system with English pretrained models. In particular, our adaptive WaveGlow model achieves an impressive MOS of 4.91, which sets a new benchmark for Kurdish speech synthesis. On one hand, this study empowers the advanced features of the TTS system for Central Kurdish, and on the other hand, it opens the doors for other dialects in Kurdish and other related languages to further develop. |
| title | Enhancing Kurdish Text-to-Speech with Native Corpus Training: A High-Quality WaveGlow Vocoder Approach |
| topic | Computation and Language Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2409.13734 |