Full-duplex speech models are moving voice interaction beyond conventional turn-taking, yet natural conversation is shaped not only by when an agent speaks, but also by how it behaves as a conversational character. We present CharDuplex, a character-driven full-duplex speech model that combines real-time spoken interac...
Donghang Wu, Yi-Si Liu, Chen Chen et al.· 0 citations
JELAR, a Joint-Embedding Predictive Architecture (JEPA)-based latent reasoning framework that conditions latent reasoning supervision on acoustic representations learned from raw waveforms, demonstrates the effectiveness of JEPA-conditioned latent reasoning as an alternative to explicit textual CoT supervision.
Donghang Wu, Haoyang Zhang, Yizhou Peng et al.· 0 citations
The results demonstrate that full-duplex interaction, speech recognition and generation, general language capabilities, and external tool use can be integrated in a single open speech-to-speech model without sacrificing real-time conversational behavior.
Jagadeesh Balam, Travis M. Bartley, Edresson Casanova et al.· 2 citations· ⚡1
Backend delegation is an effective and modular approach for combining natural duplex speech interaction with strong agentic tool-call capabilities and significantly outperforms GPT-realtime-mini and Qwen3-Omni-30B-A3B-Instruct on EVA-Bench.
Ke Hu, Slyne Deng, Chen Chen et al.· 3 citations· ⚡2
This work proposes an efficient method to add streaming ASR capabilities to an existing duplex S2S model by introducing a lightweight ASR head in parallel to the agent text head, enabling real-time user transcription while preserving full-duplex conversational capabilities including turn-taking and barge-in handling.
Ke Hu, Nourchene Ferchichi, Edresson Casanova et al.· 1 citation
VoiceChat-TTS is proposed, a low-latency, continuous, and streamable text-to-speech model for interactive agents that enables always-on, responsive speech generation while preserving modularity and high speech quality.
Edresson Casanova, Jaehyeon Kim, Mariana Graterol Fuenmayor et al.· 3 citations
This work proposes an always-on attention-coordination layer that mediates this interface and allocates human attention across one or more working agents, and introduces JarvisBench to evaluate both directions of this coordination.
JarvisBench, a benchmark for measuring the dual value of mediation in long-horizon agent workflows, is introduced and preliminary results suggest that Jarvis-style mediation can provide trace-grounded responses to user questions and improve task performance when sparse user guidance is injected at appropriate moments.
Chen Chen, Zhehuai Chen· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
