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

Abstract

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.

Stats

• citations9
• S2 citations—
• github stars0
• HF likes0
• heat score7.50
• arxiv keygao2023bypass

Related papers

• Learning From Flawed Data: Weakly Supervised Automatic Speech Recognition (2023)13.45
• Knn-ctc: Enhancing ASR Via Retrieval Of CTC Pseudo Labels (2023)11.36
• Semi-supervised Speech Recognition Via Graph-based Temporal Classification (2020)9.59
• From Weak Labels To Strong Results: Utilizing 5,000 Hours Of Noisy Classroom Transcripts With Minimal Accurate Data (2025)0.00
• Improved Mask-ctc For Non-autoregressive End-to-end ASR (2020)11.76
• Joint Masked CPC And CTC Training For ASR (2020)8.60
• Performance Improvements Of Probabilistic Transcript-adapted ASR With Recurrent Neural Network And Language-specific Constraints (2016)0.00
• Bridging The Gaps Of Both Modality And Language: Synchronous Bilingual CTC For Speech Translation And Speech Recognition (2023)4.49