mlsanityData to 14 Oct 2026

End-to-end Speech Recognition with similar length speech and text

arXiv 2510.10453 ↗First posted 12 Oct 2025cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

The mismatch of speech length and text length poses a challenge in automatic speech recognition (ASR). In previous research, various approaches have been employed to align text with speech, including the utilization of Connectionist Temporal Classification (CTC). In earlier work, a key frame mechanism (KFDS) was introduced, utilizing intermediate CTC outputs to guide downsampling and preserve keyframes, but traditional methods (CTC) failed to align speech and text appropriately when downsampling speech to a text-similar length. In this paper, we focus on speech recognition in those cases where the length of speech aligns closely with that of the corresponding text. To address this issue, we introduce two methods for alignment: a) Time Independence Loss (TIL) and b) Aligned Cross Entropy (AXE) Loss, which is based on edit distance. To enhance the information on keyframes, we incorporate frame fusion by applying weights and summing the keyframe with its context 2 frames. Experimental results on AISHELL-1 and AISHELL-2 dataset subsets show that the proposed methods outperform the previous work and achieve a reduction of at least 86% in the number of frames.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 21 references that are in the map. First posted on arXiv 12 Oct 2025.

Builds on

15 of 21 references.

References · 15

  1. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,380
  2. 2015Listen, Attend and Spellcited by 543
  3. 2017AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baselinecited by 373
  4. 2018AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scalecited by 128
  5. 2021Intermediate Loss Regularization for CTC-based Speech Recognitioncited by 96
  6. 2019CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognitioncited by 77
  7. 2020Aligned Cross Entropy for Non-Autoregressive Machine Translationcited by 65
  8. 2022WeNet 2.0: More Productive End-to-End Speech Recognition Toolkitcited by 47
  9. 2021Efficient conformer: Progressive downsampling and grouped attention for automatic speech recognitioncited by 42
  10. 2021Tiny Transducer: A Highly-efficient Speech Recognition Model on Edge Devicescited by 19
  11. 2022Accelerating RNN-T Training and Inference Using CTC guidancecited by 17
  12. 2021FSR: Accelerating the Inference Process of Transducer-Based Models by Applying Fast-Skip Regularizationcited by 11
3 more
  1. 2023Blank-regularized CTC for Frame Skipping in Neural Transducercited by 8
  2. 2023Key Frame Mechanism For Efficient Conformer Based End-to-end Speech Recognitioncited by 2
  3. 2024Skipformer: A Skip-and-Recover Strategy for Efficient Speech Recognitioncited by 2

Built on by

Not cited yet.