mlsanityData to 7 Oct 2026

Self-Attention Transducers for End-to-End Speech Recognition

arXiv 1909.13037 ↗First posted 28 Sep 2019eess.AS cs.CL cs.SDcited by 24

Not on the map. Why?

Abstract (arXiv)

Recurrent neural network transducers (RNN-T) have been successfully applied in end-to-end speech recognition. However, the recurrent structure makes it difficult for parallelization . In this paper, we propose a self-attention transducer (SA-T) for speech recognition. RNNs are replaced with self-attention blocks, which are powerful to model long-term dependencies inside sequences and able to be efficiently parallelized. Furthermore, a path-aware regularization is proposed to assist SA-T to learn alignments and improve the performance. Additionally, a chunk-flow mechanism is utilized to achieve online decoding. All experiments are conducted on a Mandarin Chinese dataset AISHELL-1. The results demonstrate that our proposed approach achieves a 21.3% relative reduction in character error rate compared with the baseline RNN-T. In addition, the SA-T with chunk-flow mechanism can perform online decoding with only a little degradation of the performance.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 10; 2022: 3; 2023: 8; 2024: 2; 2025: 1.

24 papers.

Sort:

  1. 2021Context-Aware Transformer Transducer for Speech Recognitioncited by 56
  2. 2023Efficient Sequence Transduction by Jointly Predicting Tokens and Durationscited by 56
  3. 2021Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERTcited by 31
  4. 2021Wav-BERT: Cooperative Acoustic and Linguistic Representation Learning for Low-Resource Speech Recognitioncited by 16
  5. 2023SpeechFormer++: A Hierarchical Efficient Framework for Paralinguistic Speech Processingcited by 16
  6. 2021Non-autoregressive Transformer-based End-to-end ASR using BERTcited by 13
  7. 2021FSR: Accelerating the Inference Process of Transducer-Based Models by Applying Fast-Skip Regularizationcited by 11
  8. 2021Multi-Channel Transformer Transducer for Speech Recognitioncited by 8
  9. 2021TSNAT: Two-Step Non-Autoregressvie Transformer Models for Speech Recognitioncited by 7
  10. 2022Speech-to-SQL: Towards Speech-driven SQL Query Generation From Natural Language Questioncited by 6
  11. 2023Token-Level Serialized Output Training for Joint Streaming ASR and ST Leveraging Textual Alignmentscited by 6
  12. 2021Thank you for Attention: A survey on Attention-based Artificial Neural Networks for Automatic Speech Recognitioncited by 5
12 more
  1. 2021Transformer-based end-to-end speech recognition with residual Gaussian-based self-attentioncited by 4
  2. 2021Conformer-based End-to-end Speech Recognition With Rotary Position Embeddingcited by 3
  3. 2022On the Effectiveness of Pinyin-Character Dual-Decoding for End-to-End Mandarin Chinese ASRcited by 2
  4. 2022Adaptive Sparse and Monotonic Attention for Transformer-based Automatic Speech Recognitioncited by 2
  5. 2023Dual-Attention Neural Transducers for Efficient Wake Word Spotting in Speech Recognitioncited by 2
  6. 2023Sim-T: Simplify the Transformer Network by Multiplexing Technique for Speech Recognitioncited by 2
  7. 2025Aligner-Encoders: Self-Attention Transformers Can Be Self-Transducerscited by 1
  8. 2023A Lexical-aware Non-autoregressive Transformer-based ASR Modelcited by 0
  9. 2023GNCformer Enhanced Self-attention for Automatic Speech Recognitioncited by 0
  10. 2023Improving End-to-End Speech Processing by Efficient Text Data Utilization with Latent Synthesiscited by 0
  11. 2024XCB: an effective contextual biasing approach to bias cross-lingual phrases in speech recognitioncited by 0
  12. 2024A Decade of Deep Learning: A Survey on The Magnificent Sevencited by 0