Tag
CVSS-X is a large-scale synthetic speech-to-speech translation corpus extending CVSS to enable translation from English into 28 languages, with over 16,000 hours of parallel speech pairs for bidirectional research.
This paper presents Wayu-Paxa-TTS-Edge, an 82M-parameter Thai TTS model trained on synthetic speech from a voice-cloning teacher, achieving high accuracy and prosody for on-device use without reference audio.
This paper proposes using Group Relative Policy Optimization (GRPO) for adapting LLM-based ASR models to regulated domains using only synthetic speech, achieving 40-45% relative WER reduction over supervised fine-tuning.
This paper investigates the distributional gap between synthetic and real speech in LLM-based ASR systems, identifies where the LLM separates them, and proposes using layer-selection and RIR augmentation to match real-data baselines with less real data.