Qingfeng Liu

TL;DR: A general adaptation scheme for DNN based on discriminant condition codes is proposed, which is directly fed to various layers of a pre-trained DNN through a new set of connection weights, which are quite effective to adapt large DNN models using only a small amount of adaptation data.

TL;DR: This work has shown that the training procedure of the mDNN under popular criteria, including both frame-level cross-entropy and sequence-level discriminative training, can be parallelized efficiently to yield significant speedup.

TL;DR: Experiments on single-channel CHiME-4 Challenge show that CEGM yields consistently the highest correlations with word error rate (WER) which is often costly to calculate, and achieves the most accurate assessment of ASR performance when compared to the perceptual evaluation metrics commonly used for assessing speech enhancement performance.

TL;DR: A new speaker adaptation method for the hybrid NN/HMM speech recognition model based on singular value decomposition (SVD) is proposed, which alleviates the over-fitting problem via updating the weight matrices slightly by only modifying the singular values.

TL;DR: A statistical analysis reveals the super-Gaussian and heteroscedastic properties of the prediction errors in nonlinear regression deep neural network (DNN)-based speech enhancement when estimating clean log-power spectral (LPS) components at DNN outputs with noisy LPS features in DNN input vectors.