mlsanityData to 7 Oct 2026

Bypass Temporal Classification: Weakly Supervised Automatic Speech Recognition with Imperfect Transcripts

arXiv 2306.01031 ↗First posted 1 Jun 2023cs.CL cs.LG cs.SDcited by 10

Not on the map. Why?

Abstract (arXiv)

This paper presents a novel algorithm for building an automatic speech recognition (ASR) model with imperfect training data. Imperfectly transcribed speech is a prevalent issue in human-annotated speech corpora, which degrades the performance of ASR models. To address this problem, we propose Bypass Temporal Classification (BTC) as an expansion of the Connectionist Temporal Classification (CTC) criterion. BTC explicitly encodes the uncertainties associated with transcripts during training. This is accomplished by enhancing the flexibility of the training graph, which is implemented as a weighted finite-state transducer (WFST) composition. The proposed algorithm improves the robustness and accuracy of ASR systems, particularly when working with imprecisely transcribed speech corpora. Our implementation will be open-sourced.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 9 of its 30 references that are in the map. First posted on arXiv 1 Jun 2023.

Builds on

9 of 30 references.

References · 9

  1. 2017Attention Is All You Needcited by 59,932
  2. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  3. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  4. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  5. 2015EESEN: End-to-End Speech Recognition using Deep RNN Models and WFST-based Decodingcited by 73
  6. 2020Differentiable Weighted Finite-State Transducerscited by 22
  7. 2021CTC Variations Through New WFST Topologiescited by 17
  8. 2022Star Temporal Classification: Sequence Classification with Partially Labeled Datacited by 10
  9. 2019Handling Noisy Labels for Robustly Learning from Self-Training Data for Low-Resource Sequence Labelingcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 3; 2026: 3.

10 papers.

  1. 2023Updated Corpora and Benchmarks for Long-Form Speech Recognitioncited by 10
  2. 2023Learning from Flawed Data: Weakly Supervised Automatic Speech Recognitioncited by 8
  3. 2024Token-Weighted RNN-T for Learning from Flawed Datacited by 2
  4. 2024Fast Streaming Transducer ASR Prototyping via Knowledge Distillation with Whispercited by 1
  5. 2025RNN-Transducer-based Losses for Speech Recognition on Noisy Targetscited by 1
  6. 2025WST: Weakly Supervised Transducer for Automatic Speech Recognitioncited by 1
  7. 2025Graph Connectionist Temporal Classification for Phoneme Recognitioncited by 0
  8. 2026Modeling Overlapped Speech with Shufflescited by 0
  9. 2026Constrained CTC Decoding for Efficient Diacritic Restorationcited by 0
  10. 2026A Training Criterion with Token-Level Tolerance to Transcription Ambiguity for Automatic Speech Recognitioncited by 0