Unimodal Aggregation for CTC-based Speech Recognition
This work addresses speech recognition efficiency and accuracy for Mandarin language processing, but it is incremental as it builds on existing CTC-based methods.
The paper tackles the problem of improving non-autoregressive automatic speech recognition by proposing a unimodal aggregation method to segment and integrate feature frames for better token representations, resulting in lower recognition error and computational complexity on Mandarin datasets.
This paper works on non-autoregressive automatic speech recognition. A unimodal aggregation (UMA) is proposed to segment and integrate the feature frames that belong to the same text token, and thus to learn better feature representations for text tokens. The frame-wise features and weights are both derived from an encoder. Then, the feature frames with unimodal weights are integrated and further processed by a decoder. Connectionist temporal classification (CTC) loss is applied for training. Compared to the regular CTC, the proposed method learns better feature representations and shortens the sequence length, resulting in lower recognition error and computational complexity. Experiments on three Mandarin datasets show that UMA demonstrates superior or comparable performance to other advanced non-autoregressive methods, such as self-conditioned CTC. Moreover, by integrating self-conditioned CTC into the proposed framework, the performance can be further noticeably improved.