Unimodal Aggregation for CTC-based Speech Recognition

arXiv:2309.08150v2 Announce Type: replace
Abstract: 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 …

abstract aggregation arxiv automatic speech recognition cs.cl cs.sd eess.as encoder feature features learn paper recognition segment speech speech recognition text token tokens type wise