mlsanityData to 14 Oct 2026

Improving CTC-based ASR Models with Gated Interlayer Collaboration

arXiv 2205.12462 ↗First posted 25 May 2022cs.CL cs.SD eess.AScited by 4

Not on the map. Why?

Abstract (arXiv)

The CTC-based automatic speech recognition (ASR) models without the external language model usually lack the capacity to model conditional dependencies and textual interactions. In this paper, we present a Gated Interlayer Collaboration (GIC) mechanism to improve the performance of CTC-based models, which introduces textual information into the model and thus relaxes the conditional independence assumption of CTC-based models. Specifically, we consider the weighted sum of token embeddings as the textual representation for each position, where the position-specific weights are the softmax probability distribution constructed via inter-layer auxiliary CTC losses. The textual representations are then fused with acoustic features by developing a gate unit. Experiments on AISHELL-1, TEDLIUM2, and AIDATATANG corpora show that the proposed method outperforms several strong baselines.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 30 of its 45 references that are in the map. First posted on arXiv 25 May 2022.

Builds on

30 of 45 references.

References · 30

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2016Layer Normalizationcited by 5,669
  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. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 558
  7. 2015Attention-Based Models for Speech Recognitioncited by 401
  8. 2017AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baselinecited by 373
  9. 2014Deep Speech: Scaling up end-to-end speech recognitioncited by 354
  10. 2020Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Losscited by 235
  11. 2015End-to-End Attention-based Large Vocabulary Speech Recognitioncited by 151
  12. 2020Recent Developments on ESPnet Toolkit Boosted by Conformercited by 132
18 more
  1. 2018Exploring Architectures, Data and Units For Streaming End-to-End Speech Recognition with RNN-Transducercited by 96
  2. 2021Intermediate Loss Regularization for CTC-based Speech Recognitioncited by 96
  3. 2019QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutionscited by 94
  4. 2020Mask CTC: Non-Autoregressive End-to-End ASR with CTC and Mask Predictcited by 76
  5. 2015EESEN: End-to-End Speech Recognition using Deep RNN Models and WFST-based Decodingcited by 73
  6. 2021Relaxing the Conditional Independence Assumption of CTC-based ASR by Conditioning on Intermediate Predictionscited by 61
  7. 2017Exploring Neural Transducers for End-to-End Speech Recognitioncited by 44
  8. 2021Citrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognitioncited by 34
  9. 2020Improved Mask-CTC for Non-Autoregressive End-to-End ASRcited by 32
  10. 2017Multitask Learning with Low-Level Auxiliary Tasks for Encoder-Decoder Based Speech Recognitioncited by 29
  11. 2021A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generationcited by 28
  12. 2020Improving RNN Transducer Based ASR with Auxiliary Taskscited by 27
  13. 2019Deja-vu: Double Feature Presentation and Iterated Loss in Deep Transformer Networkscited by 24
  14. 2020CASS-NAT: CTC Alignment-based Single Step Non-autoregressive Transformer for Speech Recognitioncited by 24
  15. 2018Hierarchical Multitask Learning for CTC-based Speech Recognitioncited by 14
  16. 2021Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Unitscited by 13
  17. 2015Feedforward Sequential Memory Networks: A New Structure to Learn Long-term Dependencycited by 10
  18. 2021Consistent Training and Decoding For End-to-end Speech Recognition Using Lattice-free MMIcited by 8

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 0; 2025: 1.

4 papers.

  1. 2023Improving Massively Multilingual ASR With Auxiliary CTC Objectivescited by 31
  2. 2023LAE-ST-MoE: Boosted Language-Aware Encoder Using Speech Translation Auxiliary Task for E2E Code-switching ASRcited by 6
  3. 2023SSHR: Leveraging Self-supervised Hierarchical Representations for Multilingual Automatic Speech Recognitioncited by 4
  4. 2025MGSC: A Multi-granularity Consistency Framework for Robust End-to-end Asrcited by 0