cs.CLNov 14, 2026

Low-Latency LLM-Based Streaming Multi-Talker ASR with Verifiable Rewards

Authors: Jing Pan, Ruizhi Li, Ju Lin, Jing Zheng, Florian Metze

Organizations: Meta, USA

Abstract

LLM-based architectures offer strong generalization and instruction-following capabilities for streaming automatic speech recognition (ASR), but multi-talker use introduces coupled transcription, attribution, and latency challenges. Our wearable setting requires real-time transcription of a conversation between a near-field device wearer and a far-field partner. Because partial hypotheses are rendered on persistent sides of a dialogue UI, speaker roles cannot be permuted and each speaker tag must precede its turn. These sparse tags are weakly optimized by supervised fine-tuning (SFT), while committing to a leading tag can delay the text that follows. We therefore post-train a streaming LLM-based ASR model with reinforcement learning with verifiable rewards (RLVR), combining a fixed-role Speaker-Attributed WER (SA-WER) grader with a turn-level onset-delay reward. On an eight-direction multi-talker cohort, SA-WER RL reduces SA-WER from 20.51%20.51\% for SFT to 13.14%13.14\%. Adding the delay objective reduces onset p50p50 by 65%65\% (from 0.918 s0.918\,\text{s} to 0.320 s0.320\,\text{s}) and p90p90 by 44%44\% (from 1.389 s1.389\,\text{s} to 0.780 s0.780\,\text{s}) relative to SA-WER-only RL, while achieving 12.70%12.70\% SA-WER. These results demonstrate that fixed-role recognition quality and streaming responsiveness can be improved jointly.

Figures & tables

Explore similar work

Jun 7, 2026

TRADE: Transducer-Augmented Decoder for Speech LLM

Speech Large Language Models (Speech LLMs) lack a principled mechanism for streaming inference: their label-synchronous generation has no acoustic-frame alignment, making real-time decoding and end-of-utterance detection difficult. We propose TRADE TRansducer-Augmented DEcoder, which augments a multimodal LLM with a transducer branch that shares the audio encoder and uses the LLM's hidden states directly as the prediction network -- coupling frame-synchronous acoustic alignment with the LLM's linguistic reasoning. Three design choices make the system accurate, streamable, and long-form capable: (1)Tightly coupled dual vocabularies -- a compact transducer vocabulary derived from the LLM vocabulary, enabling zero-cost score fusion; (2)Chunk-synchronized streaming training with gradient stopping, eliminating the train-inference mismatch at offline-equivalent memory cost; and (3)Localized Decoder Audio Attention (LDAA), a causal sliding window that caps KV-cache memory independently of utterance length. A single TRADE checkpoint supports offline and streaming decoding across a continuous range of latency operating points. TRADE achieves 6.71% average WER on the Open ASR Leaderboard, while the streaming recognition with 960ms chunk size reaches 8.40% from the same checkpoint. On long-form speech, it obtains 3.64% WER on TED-LIUM and 10.88% on Earnings-22 without external segmentation. TRADE provides sentence-end punctuation timestamps that, when combined with acoustic voice activity detection (VAD), improve end-of-utterance detection by +0.03 F_1 over acoustic VAD alone.
Sep 16, 2026

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

Streaming automatic speech recognition (ASR) must be judged jointly on what it transcribes and on how quickly it commits each word. Delayed streams modeling (DSM) has become the dominant paradigm for streaming large audio-language models, exposing a structural delay ττ that bounds the decoder's lookahead. We show that ττ is a poor proxy for user-perceived latency, and that the alignment-based supervision of DSM leaves latency on the table: the same forced-aligned transcript is used at every ττ, forcing the model to withhold words it could already commit. We introduce AWED, a word-level emission-delay metric defined relative to the acoustic end of each word, and post-train a DSM recognizer with GRPO under a reward that scores transcription accuracy and measured delay jointly. Trained at a single operating point (τ=6τ=6 frames), our model dominates both its supervised fine-tuning initialization and the Voxtral Realtime backbone across all evaluated lookahead budgets: it cuts WER by 30.8% relative at an 80,ms structural delay, and by 5.7% relative at 480,ms while lowering median AWED from 1.17,s to 1.04,s. Latency-rewarded post-training thus advances the accuracy--latency Pareto frontier of streaming ASR without architectural change.
Mar 11, 2026

Uni-ASR: Unified LLM-Based Architecture for Non-Streaming and Streaming Automatic Speech Recognition

Although the deep integration of the Automatic Speech Recognition (ASR) system with Large Language Models (LLMs) has significantly improved accuracy, the deployment of such systems in low-latency streaming scenarios remains challenging. In this paper, we propose Uni-ASR, a unified framework based on LLMs that integrates both non-streaming and streaming speech recognition capabilities. We propose a joint training paradigm that enables the system to seamlessly transition between two recognition modes without any architectural modifications. Furthermore, we introduce a context-aware training paradigm and a co-designed fallback decoding strategy, which can enhance streaming recognition accuracy without introducing additional latency. The experimental results demonstrate that Uni-ASR not only achieves competitive performance within non-streaming mode, but also demonstrates strong effectiveness in streaming scenarios under diverse latency constraints.