تقرير
CrossVoice: Crosslingual Prosody Preserving Cascade-S2ST using Transfer Learning
العنوان: | CrossVoice: Crosslingual Prosody Preserving Cascade-S2ST using Transfer Learning |
---|---|
المؤلفون: | Hira, Medha, Goel, Arnav, Gupta, Anubha |
سنة النشر: | 2024 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computation and Language, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing |
الوصف: | This paper presents CrossVoice, a novel cascade-based Speech-to-Speech Translation (S2ST) system employing advanced ASR, MT, and TTS technologies with cross-lingual prosody preservation through transfer learning. We conducted comprehensive experiments comparing CrossVoice with direct-S2ST systems, showing improved BLEU scores on tasks such as Fisher Es-En, VoxPopuli Fr-En and prosody preservation on benchmark datasets CVSS-T and IndicTTS. With an average mean opinion score of 3.75 out of 4, speech synthesized by CrossVoice closely rivals human speech on the benchmark, highlighting the efficacy of cascade-based systems and transfer learning in multilingual S2ST with prosody transfer. Comment: 8 pages, Accepted at ICLR 2024 - Tiny Track |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2406.00021 |
رقم الأكسشن: | edsarx.2406.00021 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |