mlsanityData to 14 Oct 2026

Towards Effective and Compact Contextual Representation for Conformer Transducer Speech Recognition Systems

arXiv 2306.13307 ↗First posted 23 Jun 2023eess.AS cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Current ASR systems are mainly trained and evaluated at the utterance level. Long range cross utterance context can be incorporated. A key task is to derive a suitable compact representation of the most relevant history contexts. In contrast to previous researches based on either LSTM-RNN encoded histories that attenuate the information from longer range contexts, or frame level concatenation of transformer context embeddings, in this paper compact low-dimensional cross utterance contextual features are learned in the Conformer-Transducer Encoder using specially designed attention pooling layers that are applied over efficiently cached preceding utterances history vectors. Experiments on the 1000-hr Gigaspeech corpus demonstrate that the proposed contextualized streaming Conformer-Transducers outperform the baseline using utterance internal context only with statistically significant WER reductions of 0.7% to 0.5% absolute (4.3% to 3.1% relative) on the dev and test data.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 33 of its 48 references that are in the map. First posted on arXiv 23 Jun 2023.

Builds on

33 of 48 references.

References · 33

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Longformer: The Long-Document Transformercited by 3,413
  3. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  4. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,850
  5. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,380
  6. 2019Compressive Transformers for Long-Range Sequence Modellingcited by 726
  7. 2016Language Modeling with Gated Convolutional Networkscited by 702
  8. 2015Listen, Attend and Spellcited by 543
  9. 2021GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audiocited by 399
  10. 2020Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Losscited by 235
  11. 2019A Comparative Study on Transformer vs RNN in Speech Applicationscited by 211
  12. 2020Recent Developments on ESPnet Toolkit Boosted by Conformercited by 132
21 more
  1. 2018Attentive Statistics Pooling for Deep Speaker Embeddingcited by 114
  2. 2014Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognitioncited by 111
  3. 2020Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Datasetcited by 97
  4. 2019Transformer-Transducer: End-to-End Speech Recognition with Self-Attentioncited by 69
  5. 2021Context-Aware Transformer Transducer for Speech Recognitioncited by 56
  6. 2021On the limit of English conversational speech recognitioncited by 30
  7. 2016Attentive Pooling Networkscited by 28
  8. 2019Transformer ASR with Contextual Block Processingcited by 28
  9. 2018Dialog-context aware end-to-end speech recognitioncited by 27
  10. 2021Advanced Long-context End-to-end Speech Recognition Using Context-expanded Transformerscited by 25
  11. 2023Diagonal State Space Augmented Transformers for Speech Recognitioncited by 25
  12. 2022Tree-constrained Pointer Generator with Graph Neural Network Encodings for Contextual Speech Recognitioncited by 17
  13. 2021Transformer Language Models with LSTM-based Cross-utterance Information Representationcited by 15
  14. 2019Gated Embeddings in End-to-End Speech Recognition for Conversational-Context Fusioncited by 14
  15. 2022Efficient Training of Neural Transducer for Speech Recognitioncited by 14
  16. 2020Contextualizing ASR Lattice Rescoring with Hybrid Pointer Network Language Modelcited by 11
  17. 2022Improving the Training Recipe for a Robust Conformer-based Hybrid Modelcited by 9
  18. 2020Speaker-aware speech-transformercited by 7
  19. 2022Leveraging Acoustic Contextual Representation by Audio-textual Cross-modal Learning for Conversational ASRcited by 7
  20. 2022Confidence Score Based Conformer Speaker Adaptation for Speech Recognitioncited by 5
  21. 2020LSTM-LM with Long-Term History for First-Pass Decoding in Conversational Speech Recognitioncited by 4

Built on by

Cited by year

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

6 papers.

  1. 2023Updated Corpora and Benchmarks for Long-Form Speech Recognitioncited by 10
  2. 2024Exploring SSL Discrete Tokens for Multilingual ASRcited by 6
  3. 2023Conversational Speech Recognition by Learning Audio-textual Cross-modal Contextual Representationcited by 4
  4. 2023Generative Context-aware Fine-tuning of Self-supervised Speech Modelscited by 3
  5. 2024Exploring SSL Discrete Speech Features for Zipformer-based Contextual ASRcited by 2
  6. 2025C2AV-TSE: Context and Confidence-aware Audio Visual Target Speaker Extractioncited by 2