2 papers
cs.SD2026
Pronunciation-Oriented Reinforcement Learning for Japanese Text-to-Speech with Kana-Domain ASR Rewards
Shiao Zhu, Lianbo Liu, Kai Washizaki +2
Character error rate (CER) computed by automatic speech recognition (ASR) is widely used as an intelligibility reward for reinforcement learning (RL) post-training of text-to-speec…
eess.AS2026
Factorized Delayed Streams Modeling for LLM-based Streaming ASR
Tatsunari Takagi, Kai Washizaki, Atsushi Kojima +3
Delayed Streams Modeling (DSM) enables LLM-based streaming automatic speech recognition (ASR) by aligning acoustic and text streams on a common timeline. DSM adds the padding token…