← Back to all news
arXiv AI By Wei-Tzu Lee, Keisuke Kamahori, Baris Kasikci

Murmur: Efficient Long-Context ASR Inference with Hierarchical Chunking

Read the original on arXiv AI →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Sep 10

X2Streaming-ASR: wait when uncertain, emit when ready for streaming ASR

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.

By Zhiwei Lin, Kaiqi Fu, Rime Wen, Zehan Liu, Shawn Qin, Roy Gan, Hao Wang, Qian Wang
agentsmultimodal
More like this →
arXiv AI
Sep 17

Look Less, Hear Better: Jointly Rewarded GRPO for Streaming ASR

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
llmsfine-tuningmultimodalsafety
More like this →
arXiv AI
Jul 7

StarTSE: Towards Streaming Target Speaker Extraction via Chunk-wise Interleaved Splicing of Autoregressive Language Model

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
llmsbenchmarks
More like this →