VAD-free Streaming Hybrid CTC/Attention ASR for Unsegmented Recording
Not on the map. Why?
Abstract (arXiv)
In this work, we propose novel decoding algorithms to enable streaming automatic speech recognition (ASR) on unsegmented long-form recordings without voice activity detection (VAD), based on monotonic chunkwise attention (MoChA) with an auxiliary connectionist temporal classification (CTC) objective. We propose a block-synchronous beam search decoding to take advantage of efficient batched output-synchronous and low-latency input-synchronous searches. We also propose a VAD-free inference algorithm that leverages CTC probabilities to determine a suitable timing to reset the model states to tackle the vulnerability to long-form data. Experimental evaluations demonstrate that the block-synchronous decoding achieves comparable accuracy to the label-synchronous one. Moreover, the VAD-free inference can recognize long-form speech robustly for up to a few hours.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 27 of its 45 references that are in the map. First posted on arXiv 15 Jul 2021.
Builds on
27 of 45 references.
References · 27
- 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
- 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
- 2015Listen, Attend and Spellcited by 542
- 2015Attention-Based Models for Speech Recognitioncited by 400
- 2016Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learningcited by 254
- 2018Correcting Length Bias in Neural Machine Translationcited by 119
- 2020Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Datasetcited by 94
- 2017Online and Linear-Time Attention by Enforcing Monotonic Alignmentscited by 85
- 2017Monotonic Chunkwise Attentioncited by 82
- 2019Recognizing long-form speech using streaming end-to-end modelscited by 77
- 2019CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognitioncited by 76
- 2017Minimum Word Error Rate Training for Attention-based Sequence-to-Sequence Modelscited by 68
15 more
- 2020FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularizationcited by 66
- 2020On the Comparison of Popular End-to-End Models for Large Scale Speech Recognitioncited by 62
- 2020Towards Fast and Accurate Streaming End-to-End ASRcited by 47
- 2017Exploring Neural Transducers for End-to-End Speech Recognitioncited by 43
- 2019A comparison of end-to-end models for long-form speech recognitioncited by 42
- 2020Alignment Restricted Streaming Recurrent Neural Network Transducercited by 42
- 2019Self-Attention Aligner: A Latency-Control End-to-End Model for ASR Using Self-Attention Network and Chunk-Hoppingcited by 33
- 2020End-to-End Automatic Speech Recognition Integrated With CTC-Based Voice Activity Detectioncited by 20
- 2020Low Latency End-to-End Streaming Speech Recognition with a Scout Networkcited by 20
- 2020Minimum Latency Training Strategies for Streaming Sequence-to-Sequence ASRcited by 19
- 2015Highway Long Short-Term Memory RNNs for Distant Speech Recognitioncited by 17
- 2021Alignment Knowledge Distillation for Online Streaming Attention-based Speech Recognitioncited by 11
- 2020A Comparison of Label-Synchronous and Frame-Synchronous End-to-End Models for Speech Recognitioncited by 8
- 2020CTC-synchronous Training for Monotonic Attention Modelcited by 3
- 2021StableEmit: Selection Probability Discount for Reducing Emission Latency of Streaming Monotonic Attention ASRcited by 1
Built on by
Citing papers per year: 2023: 1.
1 paper.