arXiv:2611.06496v1 Announce Type: new Abstract: Most speech large language models (SLMs) still process speech in an offline manner. They only start responding after they receive the complete speech s...
arXiv:2606. 05121v1 Announce Type: cross Abstract: Audio is an inherently interactive modality, yet today's Large Audio Language Models (LALMs) are offline, and streaming audio models each handle only a single task such as streaming ASR or voice chatting.
arXiv:2602. 14612v4 Announce Type: replace-cross Abstract: Answering natural-language questions over multi-hour audio requires both event recognition and temporal grounding.
Streaming speech-to-speech language models aim to answer spoken queries directly with synthetic speech. However, standard speech and text benchmarks do not capture whether these systems behave naturally in conversations, where timing, turn-taking, prosody, interpersonal stance, language and dialect consistency, and relationship-aware appropriateness jointly shape perceived quality.
arXiv:2607. 05365v1 Announce Type: cross Abstract: Streaming speech-to-speech language models aim to answer spoken queries directly with synthetic speech.
arXiv:2609.13076v1 Announce Type: cross Abstract: Conversational voice agents have advanced significantly, offering increasingly natural human-machine interactions through both cascaded and end-to-en...
arXiv:2609.22214v1 Announce Type: new Abstract: Long multilingual conversational spoken question answering requires systems to balance long-range transcript semantics with sparse acoustic and speaker...
arXiv:2606. 13544v1 Announce Type: cross Abstract: Turn-taking in multi-party spoken conversations remains a fundamental challenge for voice-based agents, particularly under dynamic floor competition and varying user expectations.
The paper presents a new wake‑up system for voice assistants that goes beyond simple keyword spotting by adding contextual trigger detection. After the wake word is heard, the system reasons to differentiate between actual user commands and unrelated speech, enabling more efficient and context‑aware interactions. A data‑generation architecture is introduced that creates a 62.3‑hour corpus of controllable multi‑speaker conversations, including direct invocations, contextual follow‑ups, and non‑addressed speech, and experimental results confirm the approach’s effectiveness across varied synthetic scenarios.
GEPARD is a streaming text‑to‑speech model that uses a standard large language model backbone to generate speech autoregressively, decoding audio with an FSQ‑based neural codec. It streams audio chunk‑by‑chunk as text arrives, achieving a real‑time factor of about 0.067 and an aggregate speedup of roughly 204× on a single GPU with 256 concurrent streams. The design keeps all complex auxiliary mechanisms outside the decode loop, enabling deployment with a standard LLM engine (vLLM) without kernel modifications.
The paper introduces a method called randomized intermediate guidance for training tandem speech-to-speech models, where a large language model (LLM) acts as a backend providing candidate responses while the user is speaking. Instead of simulating the backend’s guidance, the approach derives guidance directly from the conversation corpus, using target responses for informative guidance and randomly sampled responses to simulate irrelevant updates. Experiments on synthetic dialogues and 3.8k hours of real conversations show that this technique yields response quality comparable to LLM-generated baselines while improving natural turn‑taking and audio‑judge naturalness.
PERSIST is a persistent memory system designed for multi-session, multi-speaker spoken dialogue, explicitly modeling Who, What, and When to enable voice assistants to recall past conversations and adapt to individual users. It structures cross-session histories into readable event records and retrieves them using a 3W joint scoring mechanism that combines semantic content, acoustic speaker identity, and temporal state. By reusing intermediate representations from the dialogue backbone, PERSIST reduces retrieval latency from 578.42 ms to 7.03 ms and achieves 85.08% end‑to‑end task accuracy on the SpokenTrace benchmark, improving EM@3 from 49.01% to 82.10%.