mlsanityData to 7 Oct 2026

CUSIDE: Chunking, Simulating Future Context and Decoding for Streaming ASR

arXiv 2203.16758 ↗First posted 31 Mar 2022eess.AS cs.CLcited by 11

Not on the map. Why?

Abstract (arXiv)

History and future contextual information are known to be important for accurate acoustic modeling. However, acquiring future context brings latency for streaming ASR. In this paper, we propose a new framework - Chunking, Simulating Future Context and Decoding (CUSIDE) for streaming speech recognition. A new simulation module is introduced to recursively simulate the future contextual frames, without waiting for future context. The simulation module is jointly trained with the ASR model using a self-supervised loss; the ASR model is optimized with the usual ASR loss, e.g., CTC-CRF as used in our experiments. Experiments show that, compared to using real future frames as right context, using simulated future context can drastically reduce latency while maintaining recognition accuracy. With CUSIDE, we obtain new state-of-the-art streaming ASR results on the AISHELL-1 dataset.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 25 of its 31 references that are in the map. First posted on arXiv 31 Mar 2022.

Builds on

25 of 31 references.

References · 25

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  4. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  5. 2015Listen, Attend and Spellcited by 542
  6. 2017AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baselinecited by 364
  7. 2017Monotonic Chunkwise Attentioncited by 82
  8. 2019Generative Pre-Training for Speech with Autoregressive Predictive Codingcited by 82
  9. 2019CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognitioncited by 76
  10. 2020Streaming automatic speech recognition with the transformer modelcited by 73
  11. 2019Transformer-Transducer: End-to-End Speech Recognition with Self-Attentioncited by 68
  12. 2020Cascaded encoders for unifying streaming and non-streaming ASRcited by 51
13 more
  1. 2020Streaming Transformer-based Acoustic Models Using Self-attention with Augmented Memorycited by 35
  2. 2019Self-Attention Aligner: A Latency-Control End-to-End Model for ASR Using Self-Attention Network and Chunk-Hoppingcited by 33
  3. 2019Transformer ASR with Contextual Block Processingcited by 28
  4. 2020Transformer-based Online CTC/attention End-to-End Speech Recognition Architecturecited by 28
  5. 2021U2++: Unified Two-pass Bidirectional End-to-end Model for Speech Recognitioncited by 28
  6. 2020Enhancing Monotonic Multihead Attention for Streaming ASRcited by 16
  7. 2021Dual Causal/Non-Causal Self-Attention for Streaming End-to-End Speech Recognitioncited by 14
  8. 2020CAT: A CTC-CRF based ASR Toolkit Bridging the Hybrid and the End-to-end Approaches towards Data Efficiency and Low Latencycited by 13
  9. 2020Streaming Chunk-Aware Multihead Attention for Online End-to-End Speech Recognitioncited by 12
  10. 2021WNARS: WFST based Non-autoregressive Streaming End-to-End Speech Recognitioncited by 10
  11. 2020Universal ASR: Unifying Streaming and Non-Streaming ASR Using a Single Encoder-Decoder Modelcited by 8
  12. 2021Multi-mode Transformer Transducer with Stochastic Future Contextcited by 6
  13. 2021Head-synchronous Decoding for Transformer-based Streaming ASRcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 6; 2024: 1; 2025: 0; 2026: 2.

11 papers.

  1. 2023ZeroPrompt: Streaming Acoustic Encoders are Zero-Shot Masked LMscited by 13
  2. 2024Towards Online Continuous Sign Language Recognition and Translationcited by 13
  3. 2022Context-aware Fine-tuning of Self-supervised Speech Modelscited by 7
  4. 2023Chunked Attention-based Encoder-Decoder Model for Streaming Speech Recognitioncited by 7
  5. 2023Improved Training for End-to-End Streaming Automatic Speech Recognition Model with Punctuationcited by 3
  6. 2022SSCFormer: Push the Limit of Chunk-wise Conformer for Streaming ASR Using Sequentially Sampled Chunks and Chunked Causal Convolutioncited by 1
  7. 2023Enhancing the Unified Streaming and Non-streaming Model with Contrastive Learningcited by 0
  8. 2023DCTX-Conformer: Dynamic context carry-over for low latency unified streaming and non-streaming Conformer ASRcited by 0
  9. 2023ApproBiVT: Lead ASR Models to Generalize Better Using Approximated Bias-Variance Tradeoff Guided Early Stopping and Checkpoint Averagingcited by 0
  10. 2026SENS-ASR: Semantic Embedding injection in Neural-transducer for Streaming Automatic Speech Recognitioncited by 0
  11. 2026X2Streaming-ASR: wait when uncertain, emit when ready for streaming ASRcited by 0