Simul-Whisper: Attention-Guided Streaming Whisper with Truncation Detection

• URL: http://arxiv.org/abs/2406.10052v1
• Date: Fri, 14 Jun 2024 14:07:26 GMT
• Title: Simul-Whisper: Attention-Guided Streaming Whisper with Truncation Detection
• Abstract summary: We introduce Simul-Whisper, which uses the time alignment embedded in Whisper's cross-attention to guide auto-regressive decoding. Experiments on multiple languages and Whisper architectures show that Simul-Whisper achieves an average absolute word error rate of only 1.46% at a chunk size of 1 second.
• Score: 14.989929439744172
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As a robust and large-scale multilingual speech recognition model, Whisper has demonstrated impressive results in many low-resource and out-of-distribution scenarios. However, its encoder-decoder structure hinders its application to streaming speech recognition. In this paper, we introduce Simul-Whisper, which uses the time alignment embedded in Whisper's cross-attention to guide auto-regressive decoding and achieve chunk-based streaming ASR without any fine-tuning of the pre-trained model. Furthermore, we observe the negative effect of the truncated words at the chunk boundaries on the decoding results and propose an integrate-and-fire-based truncation detection model to address this issue. Experiments on multiple languages and Whisper architectures show that Simul-Whisper achieves an average absolute word error rate degradation of only 1.46% at a chunk size of 1 second, which significantly outperforms the current state-of-the-art baseline.

Related papers

• Beyond Clean Text: Evaluating Encoder and Decoder Robustness for Bangla Event Detection in Noisy Text [0.0]
  Event detection systems are typically evaluated on clean, curated text, leaving their robustness to real-world noise largely unexplored.<n>We introduce a generalized Bangla news event and a benchmark comprising 9,979 annotated sentences across 40 event subtypes.<n>We show that encoder models achieve higher performance on clean text but degrade substantially under noise, whereas decoder-only LLMs are markedly more robust.
  arXiv  Detail & Related papers  (2026-06-29T21:03:32Z)
• Temporal Contrastive Decoding: A Training-Free Method for Large Audio-Language Models [56.91801348360746]
  Large audio-language models (LALMs) generalize across speech, sound, and music.<n> unified decoders can exhibit a emphtemporal smoothing bias<n>We propose emphTemporal Contrastive Decoding (TCD), a training-free decoding method for unified LALMs.
  arXiv  Detail & Related papers  (2026-04-16T02:30:41Z)
• Voxtral Realtime [134.66962524291424]
  Voxtral Realtime is a streaming automatic speech recognition model.<n>It matches offline transcription quality at sub-second latency.<n>We release the model weights under the Apache 2.0 license.
  arXiv  Detail & Related papers  (2026-02-11T19:17:10Z)
• Towards Generalized Source Tracing for Codec-Based Deepfake Speech [52.68106957822706]
  We introduce the Semantic-Acoustic Source Tracing Network (SASTNet), which jointly leverages Whisper for semantic feature encoding and Wav2vec2 with AudioMAE for acoustic feature encoding.<n>Our proposed SASTNet achieves state-of-the-art performance on the CoSG test set of the CodecFake+ dataset, demonstrating its effectiveness for reliable source tracing.
  arXiv  Detail & Related papers  (2025-06-08T21:36:10Z)
• End-to-end multi-channel speaker extraction and binaural speech synthesis [26.373624846079686]
  Speech clarity and spatial audio immersion are two most critical factors in enhancing remote conferencing experiences.<n>We introduce an end-to-end deep learning framework that has the capacity of mapping multi-channel noisy and reverberant signals to clean and spatialized speech directly.<n>In this framework, a novel magnitude-weighted interaural level difference loss function is proposed that aims to improve the accuracy of spatial rendering.
  arXiv  Detail & Related papers  (2024-10-08T06:55:35Z)
• Qifusion-Net: Layer-adapted Stream/Non-stream Model for End-to-End Multi-Accent Speech Recognition [1.0690007351232649]
  We propose a layer-adapted fusion (LAF) model, called Qifusion-Net, which does not require any prior knowledge about the target accent. Experiment results demonstrate that our proposed methods outperform the baseline with relative reductions of 22.1$%$ and 17.2$%$ in character error rate (CER) across multi accent test datasets.
  arXiv  Detail & Related papers  (2024-07-03T11:35:52Z)
• Decoder-only Architecture for Streaming End-to-end Speech Recognition [45.161909551392085]
  We propose to use a decoder-only architecture for blockwise streaming automatic speech recognition (ASR) In our approach, speech features are compressed using CTC output and context embedding using blockwise speech subnetwork, and are sequentially provided as prompts to the decoder. Our proposed decoder-only streaming ASR achieves 8% relative word error rate reduction in the LibriSpeech test-other set while being twice as fast as the baseline model.
  arXiv  Detail & Related papers  (2024-06-23T13:50:08Z)
• Mixture Encoder Supporting Continuous Speech Separation for Meeting Recognition [15.610658840718607]
  We propose a mixture encoder to mitigate the effect of artifacts introduced by the speech separation. We extend this approach to more natural meeting contexts featuring an arbitrary number of speakers and dynamic overlaps. Our experiments show state-of-the-art performance on the LibriCSS dataset and highlight the advantages of the mixture encoder.
  arXiv  Detail & Related papers  (2023-09-15T14:57:28Z)
• Audio-Visual Speech Enhancement with Score-Based Generative Models [22.559617939136505]
  This paper introduces an audio-visual speech enhancement system that leverages score-based generative models. We exploit audio-visual embeddings obtained from a self-super-vised learning model that has been fine-tuned on lipreading. Experimental evaluations show that the proposed audio-visual speech enhancement system yields improved speech quality.
  arXiv  Detail & Related papers  (2023-06-02T10:43:42Z)
• There is more than one kind of robustness: Fooling Whisper with adversarial examples [28.934863462633636]
  We show that we can degrade Whisper performance dramatically, or even transcribe a target sentence of our choice. We also show that by fooling the Whisper language detector we can very easily degrade the performance of multilingual models.
  arXiv  Detail & Related papers  (2022-10-26T21:03:17Z)
• Pre-Training Transformer Decoder for End-to-End ASR Model with Unpaired Speech Data [145.95460945321253]
  We introduce two pre-training tasks for the encoder-decoder network using acoustic units, i.e., pseudo codes. The proposed Speech2C can relatively reduce the word error rate (WER) by 19.2% over the method without decoder pre-training.
  arXiv  Detail & Related papers  (2022-03-31T15:33:56Z)
• Improving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstruction [109.44933866397123]
  Noise robustness is essential for deploying automatic speech recognition systems in real-world environments. We employ a noise-robust representation learned by a refined self-supervised framework for noisy speech recognition. We achieve comparable performance to the best supervised approach reported with only 16% of labeled data.
  arXiv  Detail & Related papers  (2021-10-28T20:39:02Z)
• Wav2vec-Switch: Contrastive Learning from Original-noisy Speech Pairs for Robust Speech Recognition [52.71604809100364]
  We propose wav2vec-Switch, a method to encode noise robustness into contextualized representations of speech. Specifically, we feed original-noisy speech pairs simultaneously into the wav2vec 2.0 network. In addition to the existing contrastive learning task, we switch the quantized representations of the original and noisy speech as additional prediction targets.
  arXiv  Detail & Related papers  (2021-10-11T00:08:48Z)
• Streaming End-to-End ASR based on Blockwise Non-Autoregressive Models [57.20432226304683]
  Non-autoregressive (NAR) modeling has gained more and more attention in speech processing. We propose a novel end-to-end streaming NAR speech recognition system. We show that the proposed method improves online ASR recognition in low latency conditions.
  arXiv  Detail & Related papers  (2021-07-20T11:42:26Z)
• Audio-visual Multi-channel Recognition of Overlapped Speech [79.21950701506732]
  This paper presents an audio-visual multi-channel overlapped speech recognition system featuring tightly integrated separation front-end and recognition back-end. Experiments suggest that the proposed multi-channel AVSR system outperforms the baseline audio-only ASR system by up to 6.81% (26.83% relative) and 22.22% (56.87% relative) absolute word error rate (WER) reduction on overlapped speech constructed using either simulation or replaying of the lipreading sentence 2 dataset respectively.
  arXiv  Detail & Related papers  (2020-05-18T10:31:19Z)
• Continuous speech separation: dataset and analysis [52.10378896407332]
  In natural conversations, a speech signal is continuous, containing both overlapped and overlap-free components. This paper describes a dataset and protocols for evaluating continuous speech separation algorithms.
  arXiv  Detail & Related papers  (2020-01-30T18:01:31Z)

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.