9 citations · 9 across the 13 of their papers we have counts for
4 papers · 1 filter
Enhancing Conversational TTS with Cascaded Prompting and ICL-Based Online Reinforcement Learning
Zhicheng Ouyang, Seong-Gyun Leem, Bach Viet Do +4
Conversational AI has made significant progress, yet generating expressive and controllable text-to-speech (TTS) remains challenging. Specifically, controlling fine-grained voice s…
Aligning Paralinguistic Understanding and Generation in Speech LLMs via Multi-Task Reinforcement Learning
Jingxiang Chen, Minseok Kim, Seong-Gyun Leem +13
Speech large language models (LLMs) observe paralinguistic cues such as prosody, emotion, and non-verbal sounds--crucial for intent understanding. However, leveraging these cues fa…
Equipping LLM with Directional Multi-Talker Speech Understanding Capabilities
Ju Lin, Jing Pan, Ruizhi Li +5
Recent studies have demonstrated that prompting large language models (LLM) with audio encodings enables effective speech understanding capabilities. However, most speech LLMs are…
T-Mimi: A Transformer-based Mimi Decoder for Real-Time On-Phone TTS
Haibin Wu, Bach Viet Do, Naveen Suda +10
Neural audio codecs provide promising acoustic features for speech synthesis, with representative streaming codecs like Mimi providing high-quality acoustic features for real-time…