The paper introduces AWED, a word‑level emission‑delay metric, and demonstrates that post‑training a delayed‑streaming model with a joint reward (GRPO) improves both accuracy and latency. Using a single operating point (τ=6 frames), the method outperforms both its supervised baseline and the Voxtral Realtime backbone across all lookahead budgets, reducing WER by up to 30.8% at 80 ms delay and lowering median AWED from 1.17 s to 1.04 s.
By Xiuwen Zheng
TontaubeV1 is a streaming text‑to‑speech model that preserves natural prosody while running on a single consumer GPU. It encodes speech with a hierarchical DualCodec representation at 12.5 Hz, separating a semantic stream from successive acoustic refinements, and uses Qwen3‑derived transformers to predict the semantic stream, utterance duration, and acoustic refinements. The system supports up to one minute of reference audio for voice conditioning, streams with a 200 ms latency to first audio, and achieves real‑time factors of 0.08 (single input) and 0.02 (eight concurrent inputs).
By Fritz Cremer, Jonathan Cremer
arXiv:2610.14299v1 Announce Type: cross
Abstract: Recent Speech Full-Duplex (FDX) models are capable of engaging in naturalistic conversation by listening and speaking at the same time. Building on t...
By Yi-Jen Shih, Puyuan Peng, Haohe Liu, David Harwath, Abdelrahman Mohamed
arXiv:2601.06086v2 Announce Type: replace
Abstract: Extending large language models (LLMs) to the speech domain has recently gained significant attention. A typical approach connects a pretrained LLM...
By Yiwen Shao, Wei Liu, Jiahong Li, Tianzi Wang, Kun Wei, Meng Yu, Dong Yu
arXiv:2606. 07547v1 Announce Type: cross Abstract: Speech-based large language models are typically constrained to spoken replies, which limits their user-facing outputs to what can be verbalized and suppresses text-native capabilities such as code generation, structured analysis, and multi-step reasoning in realtime interaction, for tasks that require persistent, structured, and inspectable intermediate outputs.
By Luoyuan Zhang, Bokai Xu, Junbo Cui, Weiyue Sun, Yingjing Xu, Hanyu Liu, Yuan Yao
TontaubeV1 is a streaming text‑to‑speech model that maintains natural prosody while running on a single consumer GPU. It encodes speech with a hierarchical DualCodec representation at 12.5 Hz, separating a semantic stream from successive acoustic refinements, and uses Qwen3‑derived transformers to predict the semantic stream and add refinements. The model supports up to one minute of reference audio for voice conditioning, streams with a 200 ms latency to first audio, and achieves real‑time factors of 0.08 (single input) and 0.02 (eight concurrent inputs).
RelayS2S is a hybrid real‑time dialogue system that runs a fast duplex speech‑to‑speech path and a slow ASR‑to‑LLM path in parallel. The fast path speculatively drafts a short response prefix and streams it to TTS, while the slow path generates a higher‑quality continuation conditioned on that prefix. A lightweight verifier decides whether to commit the prefix or fall back to the cascaded pipeline, achieving much lower latency (81 ms P90 first‑chunk) while preserving 99% of the cascaded pipeline’s textual quality.
By Long Mai, Junli Liang
arXiv:2606. 10368v1 Announce Type: cross Abstract: Speech-to-text (S2T) systems for recognition (ASR) and translation (S2TT) typically generate discrete text tokens.
By Xuanchen Li, Tianrui Wang, Yuheng Lu, Zikang Huang, Yu Jiang, Chenghan Lin, Chenrui Cui, Ziyang Ma, Xingyu Ma, Chunyu Qiang, Guochen Yu, Xie Chen, Longbiao Wang, Jianwu Dang
arXiv:2604. 19635v2 Announce Type: replace-cross Abstract: While generative models have set new benchmarks for Target Speaker Extraction (TSE), their inherent reliance on global context precludes deployment in real-time applications.
By Shuhai Peng, Hui Lu, Jinjiang Liu, Liyang Chen, Guiping Zhong, Jiakui Li, Huimeng Wang, Haiyun Li, Liang Cao, Shiyin Kang, Zhiyong Wu
arXiv:2606. 09019v1 Announce Type: cross Abstract: Codec-based autoregressive (AR) speech language models have achieved strong text-to-speech (TTS) quality by modeling speech as sequences of discrete audio tokens with large pretrained backbones.
By Yejin Lee, Junwon Moon, Hyoeun Kim, Hyunjin Choi, Heeseung Kim, Kyuhong Shim
The paper introduces Convex Gate (C‑Gate), a bridge that maps each speech frame to a convex combination of frozen token embeddings, enabling a single LLM decoder to process both speech and text. Using a Whisper‑large‑v3 encoder and a partially adapted Qwen2.5‑7B‑Instruct decoder, the authors jointly train on speech recognition, emotion recognition, and spoken reasoning, achieving accurate transcription and emotion detection while maintaining strong performance on text‑only benchmarks. Analyses reveal that the fixed text embeddings can support both semantic and acoustic readouts through continuous, speech‑conditioned mixtures.
By Ming-Hao Hsu, Yuxuan Hu, Shujie Liu, Jinyu Li, Yan Lu, Zhizheng Wu
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.
By Cheng-Kuang Chang, Kai-Wei Chang, Alexander H. Liu, James Glass