Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2505.18609 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909624611897344 |
|---|---|
| author | Sankar, Ashwin Lacombe, Yoach Thomas, Sherry Varadhan, Praveen Srinivasa Gandhi, Sanchit Khapra, Mitesh M |
| author_facet | Sankar, Ashwin Lacombe, Yoach Thomas, Sherry Varadhan, Praveen Srinivasa Gandhi, Sanchit Khapra, Mitesh M |
| contents | We introduce RASMALAI, a large-scale speech dataset with rich text descriptions, designed to advance controllable and expressive text-to-speech (TTS) synthesis for 23 Indian languages and English. It comprises 13,000 hours of speech and 24 million text-description annotations with fine-grained attributes like speaker identity, accent, emotion, style, and background conditions. Using RASMALAI, we develop IndicParlerTTS, the first open-source, text-description-guided TTS for Indian languages. Systematic evaluation demonstrates its ability to generate high-quality speech for named speakers, reliably follow text descriptions and accurately synthesize specified attributes. Additionally, it effectively transfers expressive characteristics both within and across languages. IndicParlerTTS consistently achieves strong performance across these evaluations, setting a new standard for controllable multilingual expressive speech synthesis in Indian languages. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_18609 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RASMALAI: Resources for Adaptive Speech Modeling in Indian Languages with Accents and Intonations Sankar, Ashwin Lacombe, Yoach Thomas, Sherry Varadhan, Praveen Srinivasa Gandhi, Sanchit Khapra, Mitesh M Computation and Language We introduce RASMALAI, a large-scale speech dataset with rich text descriptions, designed to advance controllable and expressive text-to-speech (TTS) synthesis for 23 Indian languages and English. It comprises 13,000 hours of speech and 24 million text-description annotations with fine-grained attributes like speaker identity, accent, emotion, style, and background conditions. Using RASMALAI, we develop IndicParlerTTS, the first open-source, text-description-guided TTS for Indian languages. Systematic evaluation demonstrates its ability to generate high-quality speech for named speakers, reliably follow text descriptions and accurately synthesize specified attributes. Additionally, it effectively transfers expressive characteristics both within and across languages. IndicParlerTTS consistently achieves strong performance across these evaluations, setting a new standard for controllable multilingual expressive speech synthesis in Indian languages. |
| title | RASMALAI: Resources for Adaptive Speech Modeling in Indian Languages with Accents and Intonations |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2505.18609 |