mlsanityData to 14 Oct 2026

Synchronous Transformers for End-to-End Speech Recognition

arXiv 1912.02958 ↗First posted 6 Dec 2019eess.AS cs.CL cs.LGcited by 24

Not on the map. Why?

Abstract (arXiv)

For most of the attention-based sequence-to-sequence models, the decoder predicts the output sequence conditioned on the entire input sequence processed by the encoder. The asynchronous problem between the encoding and decoding makes these models difficult to be applied for online speech recognition. In this paper, we propose a model named synchronous transformer to address this problem, which can predict the output sequence chunk by chunk. Once a fixed-length chunk of the input sequence is processed by the encoder, the decoder begins to predict symbols immediately. During training, a forward-backward algorithm is introduced to optimize all the possible alignment paths. Our model is evaluated on a Mandarin dataset AISHELL-1. The experiments show that the synchronous transformer is able to perform encoding and decoding synchronously, and achieves a character error rate of 8.91% on the test set.

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). First posted on arXiv 6 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 8; 2022: 4; 2023: 10; 2024: 1; 2025: 1.

24 papers.

Sort:

By area:

  1. 2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 140
  2. 2023End-to-End Speech Recognition: A Surveycited by 129
  3. 2021What all do audio transformer models hear? Probing Acoustic Representations for Language Delivery and its Structurecited by 52
  4. 2023Transformers in Speech Processing: A Surveycited by 39
  5. 2021Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERTcited by 31
  6. 2021U2++: Unified Two-pass Bidirectional End-to-end Model for Speech Recognitioncited by 29
  7. 2023Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognitioncited by 25
  8. 2022Variable Attention Masking for Configurable Transformer Transducer Speech Recognitioncited by 14
  9. 2021FSR: Accelerating the Inference Process of Transducer-Based Models by Applying Fast-Skip Regularizationcited by 11
  10. 2021Wake Word Detection with Streaming Transformerscited by 10
  11. 2023Chunked Attention-based Encoder-Decoder Model for Streaming Speech Recognitioncited by 7
  12. 2024Simul-Whisper: Attention-Guided Streaming Whisper with Truncation Detectioncited by 7
12 more
  1. 2023Token-Level Serialized Output Training for Joint Streaming ASR and ST Leveraging Textual Alignmentscited by 6
  2. 2021Thank you for Attention: A survey on Attention-based Artificial Neural Networks for Automatic Speech Recognitioncited by 5
  3. 2023Training-Free Acceleration of ViTs with Delayed Spatial Mergingcited by 3
  4. 2022Shifted Chunk Encoder for Transformer Based Streaming End-to-End ASRcited by 2
  5. 2023Sim-T: Simplify the Transformer Network by Multiplexing Technique for Speech Recognitioncited by 2
  6. 2021StreaMulT: Streaming Multimodal Transformer for Heterogeneous and Arbitrary Long Sequential Datacited by 1
  7. 2022SSCFormer: Push the Limit of Chunk-wise Conformer for Streaming ASR Using Sequentially Sampled Chunks and Chunked Causal Convolutioncited by 1
  8. 2025MFLA: Monotonic Finite Look-ahead Attention for Streaming Speech Recognitioncited by 1
  9. 2022FusionFormer: Fusing Operations in Transformer for Efficient Streaming Speech Recognitioncited by 0
  10. 2023GNCformer Enhanced Self-attention for Automatic Speech Recognitioncited by 0
  11. 2023Streaming Speech-to-Confusion Network Speech Recognitioncited by 0
  12. 2023Improving CTC-AED model with integrated-CTC and auxiliary loss regularizationcited by 0