Speaker adaptation of hybrid NN/HMM model for speech recognition based on singular value decomposition

• Published in: The 9th International Symposium on Chinese Spoken Language Processing pp. 1 - 5
• Main Authors: Shaofei Xue, Hui Jiang, Lirong Dai
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.09.2014
• Subjects: Adaptation models; Deep Neural Network (DNN); Hidden Markov models; Hybrid DNN/HMM; Matrix decomposition; Neural networks; Signal processing; singular value decomposition (SVD); Speaker Adaptation; Speech; Speech recognition

Recently several speaker adaptation methods have been proposed for deep neural network (DNN) in many large vocabulary continuous speech recognition (LVCSR) tasks. However, only a few methods rely on tuning the weight matrices in trained DNNs to optimize system performance since it is very prone to o...