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

• URL: http://arxiv.org/abs/2609.08672v2
• Date: Tue, 15 Sep 2026 09:12:31 GMT
• Title: X2Streaming-ASR: wait when uncertain, emit when ready for streaming ASR
• Abstract summary: X2Streaming-ASR decomposes streaming recognition into when to commit and what to commit.<n>It achieves the best streaming CER among evaluated systems on AISHELL-1 and AISHELL-3 with substantially lower latency.
• Score: 7.5375389420656225
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Streaming automatic speech recognition (ASR) for real-time voice agents and full-duplex dialogue must provide accurate partial transcripts with low commit latency. Existing systems commonly use a fixed chunk size, look-ahead, or target delay, or encourage emissions near estimated acoustic boundaries. These approaches do not directly optimize how much additional context to use at each output position under a single-pass, hard-commit constraint. We propose X2Streaming-ASR, which decomposes streaming recognition into when to commit and what to commit. Its three-stage training procedure first establishes streaming recognition ability, then warm-starts the commit policy with automatically probed trajectories, and finally refines the policy using character-level, segment-assigned group-relative rewards for recognition accuracy and latency. Across AISHELL-1/2/3 and WenetSpeech, X2Streaming-ASR achieves a mean character-level commit latency of 24-97 ms relative to forced-aligned character endpoints, compared with 409-585 ms for the evaluated streaming baselines. It achieves the best streaming CER among the evaluated systems on AISHELL-1 and AISHELL-3 with substantially lower latency.

Related papers

• Moonshine v2: Ergodic Streaming Encoder ASR for Latency-Critical Speech Applications [0.8691520242484038]
  Full-attention Transformer encoders remain a strong accuracy baseline for automatic speech recognition (ASR)<n>We introduce v2, an ergodic streaming-encoder ASR model that employs sliding-window self-attention to achieve bounded, low-latency inference.<n>Our models achieve state of the art word error rates across standard benchmarks, attaining accuracy on-par with models 6x their size while running significantly faster.
  arXiv  Detail & Related papers  (2026-02-12T18:20:45Z)
• Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage [66.67531241554546]
  End-to-end speech-in speech-out dialogue systems are emerging as a powerful alternative to traditional ASR-LLM-TTS pipelines.<n>We introduce the first approach to extend tool use directly into speech-in speech-out systems.<n>We propose Streaming Retrieval-Augmented Generation (Streaming RAG), a novel framework that reduces user-perceived latency by predicting tool queries in parallel with user speech.
  arXiv  Detail & Related papers  (2025-10-02T14:18:20Z)
• Whisfusion: Parallel ASR Decoding via a Diffusion Transformer [7.327454599174306]
  Whisfusion is a framework to fuse a pre-trained Whisper encoder with a text diffusion decoder.<n>A lightweight cross-attention adapter trained via parameter-efficient fine-tuning (PEFT) bridges the two modalities.<n>Fine-tuned solely on LibriSpeech (960h), Whisfusion achieves a lower WER than Whisper-tiny, and offers comparable latency on short audio.
  arXiv  Detail & Related papers  (2025-08-09T17:20:54Z)
• StreamMel: Real-Time Zero-shot Text-to-Speech via Interleaved Continuous Autoregressive Modeling [50.537794606598254]
  StreamMel is a pioneering single-stage streaming TTS framework that models continuous mel-spectrograms.<n>It enables low-latency, autoregressive synthesis while preserving high speaker similarity and naturalness.<n>It even achieves performance comparable to offline systems while supporting efficient real-time generation.
  arXiv  Detail & Related papers  (2025-06-14T16:53:39Z)
• Joint Optimization of Streaming and Non-Streaming Automatic Speech Recognition with Multi-Decoder and Knowledge Distillation [44.94458898538114]
  We present joint optimization of streaming and non-streaming ASR based on multi-decoder and knowledge distillation. Evaluation results show 2.6%-5.3% relative character error rate reductions (CERR) on CSJ for streaming ASR, and 8.3%-9.7% relative CERRs for non-streaming ASR within a single model.
  arXiv  Detail & Related papers  (2024-05-22T10:17:30Z)
• DCTX-Conformer: Dynamic context carry-over for low latency unified streaming and non-streaming Conformer ASR [20.42366884075422]
  We propose the integration of a novel dynamic contextual carry-over mechanism in a state-of-the-art unified ASR system. Our proposed dynamic context Conformer (DCTX-Conformer) utilizes a non-overlapping contextual carry-over mechanism. We outperform the SOTA by a relative 25.0% word error rate, with a negligible latency impact due to the additional context embeddings.
  arXiv  Detail & Related papers  (2023-06-13T23:42:53Z)
• Streaming Audio-Visual Speech Recognition with Alignment Regularization [69.30185151873707]
  We propose a streaming AV-ASR system based on a hybrid connectionist temporal classification ( CTC)/attention neural network architecture. The proposed AV-ASR model achieves WERs of 2.0% and 2.6% on the Lip Reading Sentences 3 dataset in an offline and online setup.
  arXiv  Detail & Related papers  (2022-11-03T20:20:47Z)
• Unified End-to-End Speech Recognition and Endpointing for Fast and Efficient Speech Systems [17.160006765475988]
  We propose a method to jointly train the ASR and EP tasks in a single end-to-end (E2E) model. We introduce a "switch" connection, which trains the EP to consume either the audio frames directly or low-level latent representations from the ASR model. This results in a single E2E model that can be used during inference to perform frame filtering at low cost.
  arXiv  Detail & Related papers  (2022-11-01T23:43:15Z)
• Dual Causal/Non-Causal Self-Attention for Streaming End-to-End Speech Recognition [58.69803243323346]
  Attention-based end-to-end automatic speech recognition (ASR) systems have recently demonstrated state-of-the-art results for numerous tasks. However, the application of self-attention and attention-based encoder-decoder models remains challenging for streaming ASR. We present the dual causal/non-causal self-attention architecture, which in contrast to restricted self-attention prevents the overall context to grow beyond the look-ahead of a single layer.
  arXiv  Detail & Related papers  (2021-07-02T20:56:13Z)
• Advanced Long-context End-to-end Speech Recognition Using Context-expanded Transformers [56.56220390953412]
  We extend our prior work by introducing the Conformer architecture to further improve the accuracy. We demonstrate that the extended Transformer provides state-of-the-art end-to-end ASR performance.
  arXiv  Detail & Related papers  (2021-04-19T16:18:00Z)
• FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization [78.46088089185156]
  Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as quickly and accurately as possible. Existing approaches penalize emission delay by manipulating per-token or per-frame probability prediction in sequence transducer models. We propose a sequence-level emission regularization method, named FastEmit, that applies latency regularization directly on per-sequence probability in training transducer models.
  arXiv  Detail & Related papers  (2020-10-21T17:05:01Z)
• Streaming automatic speech recognition with the transformer model [59.58318952000571]
  We propose a transformer based end-to-end ASR system for streaming ASR. We apply time-restricted self-attention for the encoder and triggered attention for the encoder-decoder attention mechanism. Our proposed streaming transformer architecture achieves 2.8% and 7.2% WER for the "clean" and "other" test data of LibriSpeech.
  arXiv  Detail & Related papers  (2020-01-08T18:58:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.