CrossVoice: Crosslingual Prosody Preserving Cascade-S2ST using Transfer Learning

2024/05/23 by Hira, Medha, Goel, Arnav, Gupta, Anubha
#Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2406.00021

Abstract

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.

Related

• Multilingual Prosody Transfer: Comparing Supervised & Transfer Learning
• Direct Speech to Speech Translation: A Review
• Transfer Learning from Monolingual ASR to Transcription-free Cross-lingual Voice Conversion
• A Holistic Cascade System, benchmark, and Human Evaluation Protocol for Expressive Speech-to-Speech Translation
• S2ST-Omni: An Efficient Multilingual Speech-to-Speech Translation Framework via Seamless Speech-Text Alignment and Progressive Fine-tuning