2 Westlake University & Westlake Institute for Advanced Study

UMA-SPLIT: UNIMODAL AGGREGATION FOR BOTH ENGLISH AND MANDARIN NON-AUTOREGRESSIVE SPEECH RECOGNITION

This paper proposes a unimodal aggregation (UMA) based nonautoregressive model for both English and Mandarin speech recognition. The original UMA explicitly segments and aggregates acoustic frames (with unimodal weights that first monotonically increase and then decrease) of the same text token to l…