mlsanityData to 7 Oct 2026

Improving CTC-AED model with integrated-CTC and auxiliary loss regularization

arXiv 2308.08449 ↗First posted 15 Aug 2023cs.CL cs.SD eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

Connectionist temporal classification (CTC) and attention-based encoder decoder (AED) joint training has been widely applied in automatic speech recognition (ASR). Unlike most hybrid models that separately calculate the CTC and AED losses, our proposed integrated-CTC utilizes the attention mechanism of AED to guide the output of CTC. In this paper, we employ two fusion methods, namely direct addition of logits (DAL) and preserving the maximum probability (PMP). We achieve dimensional consistency by adaptively affine transforming the attention results to match the dimensions of CTC. To accelerate model convergence and improve accuracy, we introduce auxiliary loss regularization for accelerated convergence. Experimental results demonstrate that the DAL method performs better in attention rescoring, while the PMP method excels in CTC prefix beam search and greedy search.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 34 references that are in the map. First posted on arXiv 15 Aug 2023.

Builds on

27 of 34 references.

References · 27

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  3. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  4. 2013Speech Recognition with Deep Recurrent Neural Networkscited by 666
  5. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 554
  6. 2015Listen, Attend and Spellcited by 542
  7. 2015Attention-Based Models for Speech Recognitioncited by 400
  8. 2017AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baselinecited by 364
  9. 2016Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learningcited by 254
  10. 2020Recent Developments on ESPnet Toolkit Boosted by Conformercited by 132
  11. 2021WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkitcited by 123
  12. 2020A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latencycited by 99
15 more
  1. 2021Intermediate Loss Regularization for CTC-based Speech Recognitioncited by 95
  2. 2017Monotonic Chunkwise Attentioncited by 82
  3. 2020Mask CTC: Non-Autoregressive End-to-End ASR with CTC and Mask Predictcited by 75
  4. 2020A Better and Faster End-to-End Model for Streaming ASRcited by 68
  5. 2020Imputer: Sequence Modelling via Imputation and Dynamic Programmingcited by 65
  6. 2019Two-Pass End-to-End Speech Recognitioncited by 62
  7. 2021Relaxing the Conditional Independence Assumption of CTC-based ASR by Conditioning on Intermediate Predictionscited by 61
  8. 2020Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognitioncited by 37
  9. 2019Synchronous Transformers for End-to-End Speech Recognitioncited by 24
  10. 2020Insertion-Based Modeling for End-to-End Automatic Speech Recognitioncited by 13
  11. 2021FSR: Accelerating the Inference Process of Transducer-Based Models by Applying Fast-Skip Regularizationcited by 11
  12. 2021Have best of both worlds: two-pass hybrid and E2E cascading framework for speech recognitioncited by 7
  13. 2021SRU++: Pioneering Fast Recurrence with Attention for Speech Recognitioncited by 6
  14. 2022Non-Autoregressive ASR with Self-Conditioned Folded Encoderscited by 5
  15. 2020One In A Hundred: Select The Best Predicted Sequence from Numerous Candidates for Streaming Speech Recognitioncited by 4

Built on by

Not cited yet.