Đang chuẩn bị liên kết để tải về tài liệu:
ASR - VLSP 2021: Automatic speech recognition with blank label re-weighting

End-to-end models have significant potential in most languages and recently proved their robustness in ASR tasks. Many robust architectures are proposed, and among many techniques, Recurrent Neural Network – Transducer (RNN-T) shows remarkable success. However, with background noise or reverb in spontaneous speech, this architecture generally suffers from high deletion error problems. |