arXiv:2606. 11386v1 Announce Type: cross Abstract: Full-duplex spoken language models (FD-SLMs) enable seamless speech interaction by allowing models to listen and speak simultaneously, yet the internal mechanism by which they coordinate listening and speaking remains underexplored.
The paper introduces asymmetric classifier‑free guidance (CFG) for target‑speaker ASR using Whisper, where a speaker‑conditioned branch predicts the target transcript and a speaker‑unconditioned branch predicts serialized multi‑speaker transcripts. CFG modulates the influence of speaker conditioning during decoding via a single guidance scale, which is first set globally on development data and then refined per utterance by a lightweight encoder‑based predictor while keeping the recognition model fixed. The resulting system yields up to 21.8% relative WER reduction over a condition‑only baseline and 5.6% over standard conditional decoding under domain shifts.
arXiv:2609.13445v1 Announce Type: new Abstract: Speech-to-speech LLMs like Moshi, and its derivative PersonaPlex, can listen and speak concurrently through full-duplex generation. However, they can b...
arXiv:2608. 13817v1 Announce Type: cross Abstract: Human speech production is constrained by physiology, giving rise to characteristic temporal structure on acoustic signals.
arXiv:2606. 07080v1 Announce Type: cross Abstract: We present dots.
arXiv:2611.00690v1 Announce Type: cross Abstract: Speech-to-speech translation (S2ST) increasingly preserves what is said and how it sounds, but not necessarily when speech and silence occur. For dub...
The paper investigates whether audio large language models (Audio LLMs) can detect when their own transcriptions are unreliable. It finds that the models are poor at self-assessment and that existing methods offer limited detection. By leveraging audio-encoder representations, the authors develop a lightweight predictor that accurately flags unreliable transcriptions and can prompt user clarification without altering the underlying model.
arXiv:2610.32349v1 Announce Type: new Abstract: Full-duplex speech models listen and speak at the same time, which makes them promising for natural, open-ended conversation. But can they sustain a co...
arXiv:2606. 14459v1 Announce Type: cross Abstract: Modern Automatic Speech Recognition (ASR) systems have made remarkable progress on standard benchmarks, yet performance gaps have emerged under real-world distribution shifts, caused by recording conditions, accents, speech impairments, and noise.
arXiv:2608. 08638v1 Announce Type: cross Abstract: Zero-shot text-to-speech (TTS) now supports interactive assistants, personalized media, and accessibility tools.
arXiv:2606. 13121v1 Announce Type: cross Abstract: Simultaneous speech-to-speech translation aims to enable near-real-time communication by minimizing latency, offering a compelling, real-time alternative to the high latency of consecutive translation.
arXiv:2607. 05364v1 Announce Type: cross Abstract: Modern autoregressive ASR systems can emit timestamps as decoded tokens, enabling timestamped transcription without frame-level aligners or inference-time post-processing.