2024/03/28 by Yuya Fujita, Fujita, Yuya, Shinji Watanabe +5
Engineering · #Audio and Speech Processing (eess.AS) #FOS: Electrical engineering #Fault Detection and Control Systems #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2403.19207
openalex publication_date 2024/03/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Non-autoregressive (NAR) models for automatic speech recognition (ASR) aim to achieve high accuracy and fast inference by simplifying the autoregressive (AR) generation process of conventional models. Connectionist temporal classification (CTC) is one of the key techniques used in NAR ASR models. In this paper, we propose a new model combining CTC and a latent variable model, which is one of the state-of-the-art models in the neural machine translation research field. A new neural network architecture and formulation specialized for ASR application are introduced. In the proposed model, CTC alignment is assumed to be dependent on the latent variables that are expected to capture dependencies between tokens. Experimental results on a 100 hours subset of Librispeech corpus showed the best recognition accuracy among CTC-based NAR models. On the TED-LIUM2 corpus, the best recognition accuracy is achieved including AR E2E models with faster inference speed.