2 papers
eess.AS2026
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…
eess.AS2025
Distributed Asynchronous Device Speech Enhancement via Windowed Cross-Attention
Gene-Ping Yang, Sebastian Braun
The increasing number of microphone-equipped personal devices offers great flexibility and potential using them as ad-hoc microphone arrays in dynamic meeting environments. However…