mlsanityData to 14 Oct 2026

Chunked Attention-based Encoder-Decoder Model for Streaming Speech Recognition

arXiv 2309.08436 ↗First posted 15 Sep 2023eess.AS cs.SD stat.MLcited by 7

Not on the map. Why?

Abstract (arXiv)

We study a streamable attention-based encoder-decoder model in which either the decoder, or both the encoder and decoder, operate on pre-defined, fixed-size windows called chunks. A special end-of-chunk (EOC) symbol advances from one chunk to the next chunk, effectively replacing the conventional end-of-sequence symbol. This modification, while minor, situates our model as equivalent to a transducer model that operates on chunks instead of frames, where EOC corresponds to the blank symbol. We further explore the remaining differences between a standard transducer and our model. Additionally, we examine relevant aspects such as long-form speech generalization, beam size, and length normalization. Through experiments on Librispeech and TED-LIUM-v2, and by concatenating consecutive sequences for long-form trials, we find that our streamable model maintains competitive performance compared to the non-streamable variant and generalizes very well to long-form speech.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 40 of its 52 references that are in the map. First posted on arXiv 15 Sep 2023.

Builds on

40 of 52 references.

References · 40

  1. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  2. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  3. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  4. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  5. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,380
  6. 2016TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systemscited by 664
  7. 2015Listen, Attend and Spellcited by 543
  8. 2015Attention-Based Models for Speech Recognitioncited by 401
  9. 2023Google USM: Scaling Automatic Speech Recognition Beyond 100 Languagescited by 231
  10. 2023End-to-End Speech Recognition: A Surveycited by 129
  11. 2018Correcting Length Bias in Neural Machine Translationcited by 120
  12. 2020Emformer: Efficient Memory Transformer Based Acoustic Model For Low Latency Streaming Speech Recognitioncited by 113
28 more
  1. 2020Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Datasetcited by 97
  2. 2017Monotonic Chunkwise Attentioncited by 83
  3. 2019Recognizing long-form speech using streaming end-to-end modelscited by 77
  4. 2016Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activationscited by 54
  5. 2017Advances in Joint CTC-Attention based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LMcited by 43
  6. 2019A comparison of end-to-end models for long-form speech recognitioncited by 42
  7. 2020Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognitioncited by 39
  8. 2020Single headed attention based sequence-to-sequence model for state-of-the-art results on Switchboardcited by 36
  9. 2020A New Training Pipeline for an Improved Neural Transducercited by 34
  10. 2019Self-Attention Aligner: A Latency-Control End-to-End Model for ASR Using Self-Attention Network and Chunk-Hoppingcited by 33
  11. 2018RETURNN as a Generic Flexible Neural Toolkit with Application to Translation and Speech Recognitioncited by 30
  12. 2019Transformer ASR with Contextual Block Processingcited by 28
  13. 2021Librispeech Transducer Model with Internal Language Model Prior Correctioncited by 26
  14. 2021Investigating Methods to Improve Language Model Integration for Attention-based Encoder-Decoder ASR Modelscited by 25
  15. 2019Synchronous Transformers for End-to-End Speech Recognitioncited by 24
  16. 2020Low Latency End-to-End Streaming Speech Recognition with a Scout Networkcited by 20
  17. 2016Length bias in Encoder Decoder Models and a Case for Global Conditioningcited by 14
  18. 2021Dual Causal/Non-Causal Self-Attention for Streaming End-to-End Speech Recognitioncited by 14
  19. 2022Variable Attention Masking for Configurable Transformer Transducer Speech Recognitioncited by 14
  20. 2022CUSIDE: Chunking, Simulating Future Context and Decoding for Streaming ASRcited by 11
  21. 2020Online Automatic Speech Recognition with Listen, Attend and Spell Modelcited by 10
  22. 2022Conformer with dual-mode chunked attention for joint online and offline ASRcited by 10
  23. 2020Neural Simultaneous Speech Translation Using Alignment-Based Chunkingcited by 8
  24. 2017Improving the Performance of Online Neural Transducer Modelscited by 7
  25. 2021A study of latent monotonic attention variantscited by 5
  26. 2021Equivalence of Segmental and Neural Transducer Modeling: A Proof of Conceptcited by 5
  27. 2020Robust Beam Search for Encoder-Decoder Attention Based Speech Recognition without Length Biascited by 4
  28. 2022Monotonic segmental attention for automatic speech recognitioncited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 1; 2026: 2.

7 papers.

  1. 2024Efficient Streaming LLM for Speech Recognitioncited by 12
  2. 2024The Conformer Encoder May Reverse the Time Dimensioncited by 2
  3. 2025Pace: Physics-Aware Attentive Temporal Convolutional Network for Battery Health Estimationcited by 2
  4. 2023Weak Alignment Supervision from Hybrid Model Improves End-to-end ASRcited by 1
  5. 2024Alternating Weak Triphone/BPE Alignment Supervision from Hybrid Model Improves End-to-End ASRcited by 0
  6. 2026Chunk-wise Attention Transducers for Fast and Accurate Streaming Speech-to-Textcited by 0
  7. 2026SENS-ASR: Semantic Embedding injection in Neural-transducer for Streaming Automatic Speech Recognitioncited by 0