SteerDuplex: Steerable Duplex Speech Dialogue Models
Full-duplex spoken dialogue models support low-latency turn taking, interruption handling, and backchanneling, yet a key capability remains underexplored: steerability, the ability to reliably shift conversational behavior along attributes such as tone, persona, speaking rate, and voice style in response to user instru...
Utkarsh Tyagi, Ramaneswaran Selvakumar, Advait Gosai et al.
· 2 citations