Bypass Temporal Classification: Weakly Supervised Automatic Speech Recognition with Imperfect Transcripts
This addresses a prevalent issue in human-annotated speech corpora for ASR developers, though it is incremental as it builds on existing CTC methods.
The paper tackles the problem of imperfect transcripts degrading ASR model performance by proposing Bypass Temporal Classification (BTC), an expansion of CTC that encodes transcript uncertainties during training, resulting in improved robustness and accuracy for ASR systems.
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.