UNSUPERVISED SPEAKER ADAPTATION USING ATTENTION-BASED SPEAKER MEMORY FOR END-TO-END ASR

An Ontology-Aware Framework for Audio Event Classification

Alignment-length synchronous decoding for RNN transducer

論文紹介: Direct-Path Signal Cross-Correlation Estimation for Sound Source Localization in Reverberation

Unsupervised training of neural mask-based beamforming

Sparse Approximation of Gram Matrices for GMMN-based Speech Synthesis

The USTC System for Blizzard Challenge 2019