Full-duplex speech models can listen and speak simultaneously, enabling natural interaction, but become increasingly difficult to control as the conversation history grows. When used as user simulators, this lack of control can cause them to deviate from prescribed scenarios and produce unreliable evaluation outcomes....
Hao-Long Zheng, Maike Züfle, Dominik Machácek et al.· 0 citations
AVMeme Exam, a human-curated benchmark of over one thousand iconic Internet sounds and videos spanning speech, songs, music, and sound effects, is introduced, showing current models perform poorly on textless music and sound effects, and struggle to think in context and in culture compared to surface content.
Low-latency, low-compute speech enhancement is essential for wearable devices with real-time communication requirements, but strict computational constraints significantly limit on-device performance. Knowledge Boosting has been proposed as an effective approach to improve edge model performance by leveraging a more ca...
Xulin Fan, Juan Azcarreta, Ashutosh Pandey et al.· 0 citations
This work introduces Few-Shot Aware GRPO (FSA-GRPO), an RL-based post-training recipe that uses a specially designed reward to encourage the model to leverage few-shot demonstrations, thereby strengthening its few-shot adaptation ability.
Haolong Zheng, Siyin Wang, Xulin Fan et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.