X
Xiaojun Qian
Researcher at The Chinese University of Hong Kong
Publications - 22
Citations - 1058
Xiaojun Qian is an academic researcher from The Chinese University of Hong Kong. The author has contributed to research in topics: Speech synthesis & Hidden Markov model. The author has an hindex of 13, co-authored 22 publications receiving 953 citations. Previous affiliations of Xiaojun Qian include Microsoft.
Papers
More filters
Journal ArticleDOI
Deep Learning for Acoustic Modeling in Parametric Speech Generation: A systematic review of existing techniques and future trends
Zhen-Hua Ling,Shiyin Kang,Heiga Zen,Andrew W. Senior,Mike Schuster,Xiaojun Qian,Helen Meng,Li Deng +7 more
TL;DR: In this article, Hidden Markov Models (HMMs) and Gaussian Mixture Models (GMMs) are used for generating low-level speech waveforms from high-level symbolic inputs via intermediate acoustic feature sequences.
Deep Learning for Acoustic Modeling in Parametric Speech Generation
Zhen-Hua Ling,Shiyin Kang,Heiga Zen,Andrew W. Senior,Mike Schuster,Xiaojun Qian,Helen Meng,Li Deng +7 more
TL;DR: This article systematically reviews emerging speech generation approaches with the dual goal of helping readers gain a better understanding of the existing techniques as well as stimulating new work in the burgeoning area of deep learning for parametric speech generation.
Journal ArticleDOI
Mispronunciation Detection and Diagnosis in L2 English Speech Using Multidistribution Deep Neural Networks
Kun Li,Xiaojun Qian,Helen Meng +2 more
TL;DR: An acoustic-graphemic-phonemic model (AGPM) using a multidistribution DNN, whose input features include acoustic features, as well as corresponding graphemes and canonical transcriptions (encoded as binary vectors), which develops a unified MDD framework which works much like free-phone recognition.
Proceedings ArticleDOI
Multi-distribution deep belief network for speech synthesis
TL;DR: Compared with the predominant HMM-based approach, objective evaluation shows that the spectrum generated from DBN has less distortion, and the overall quality is comparable to that of context-independent HMM.
Proceedings Article
Implementation of an extended recognition network for mispronunciation detection and diagnosis in computer-assisted pronunciation training.
TL;DR: A set of context-sensitive phonological rules based on cross-language (Cantonese versus English) analysis which has also been validated against common mispronunciations observed from the learners interlanguage are developed.