The paper introduces Murmur, an inference system that uses hierarchical chunking to improve long-form automatic speech recognition (ASR). By decoding intermediate target chunks in parallel and employing a fast short-window ASR for speculative drafting, Murmur achieves a 2.5× reduction in end-to-end latency while also lowering tcpWER by 1.9 points on average across English and Mandarin meeting datasets.
arXiv:2606. 01483v1 Announce Type: cross Abstract: Long-form automatic speech recognition (ASR) requires both high accuracy and low latency, but existing systems force a trade-off between the two.
X2Streaming-ASR introduces a method for streaming automatic speech recognition that separates the decision of when to commit a transcript from what to commit. The approach uses a three‑stage training process: first establishing streaming capability, then warm‑starting a commit policy with automatically probed trajectories, and finally refining the policy with character‑level, segment‑assigned group‑relative rewards for accuracy and latency. On AISHELL‑1/2/3 and WenetSpeech datasets, the system achieves mean character‑level commit latencies of 27–84 ms, far lower than baseline systems, while also attaining the best streaming character error rates on AISHELL‑1 and AISHELL‑3.
arXiv:2608. 08569v1 Announce Type: new Abstract: Recent advancements in Speech Large Language Models have demonstrated remarkable capabilities in understanding complex audio tasks.
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.
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.
arXiv:2607. 20086v1 Announce Type: cross Abstract: State-space sequence models are attractive for streaming speech because they maintain compact recurrent state, but scan-style training kernels can have unfavorable constants for short audio tasks.
arXiv:2508. 07048v2 Announce Type: replace-cross Abstract: Autoregressive (AR) encoder-decoder models dominate high-quality multilingual ASR, but their left-to-right decoders make inference latency scale with transcript length.
Omnilingual-MsASR is a new benchmark designed to evaluate omni‑modal large language models on long‑form, multi‑speaker automatic speech recognition across six languages, with recordings up to 30 minutes and up to 20 speakers. The benchmark provides parallel audio and video inputs to test cross‑modal consistency and the models’ ability to use complementary cues from both modalities. Evaluations of leading omni‑modal LLMs show significant performance gaps, with many models achieving word error rates above 100%, underscoring challenges in temporal localization, speaker disambiguation, and cross‑modal synergy.
arXiv:2609.14991v1 Announce Type: new Abstract: Open Thai automatic speech recognition (ASR) is dominated by offline, Whisper-based models that read the whole utterance before transcribing, ruling ou...
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...
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).
Confucius4‑R2T2, a stable‑prefix streaming ASR model, is introduced to ensure that once a token is emitted it is never revised, thereby reducing wasted work and incorrect actions in real‑time transcription. The model is derived by post‑training Qwen3‑ASR‑1.7B on 1,500 hours of Chinese and English audio while keeping its audio encoder frozen, and it leverages a new concept called Longest Stable Prefix (LSP) to convert a full‑context model into a stable‑prefix streaming one without architectural changes. Evaluation shows that R2T2 achieves near full‑context quality with low latency and stable output, and its benefits generalize beyond the languages used in training.