X
Xinhui Zhou
Researcher at University of Maryland, College Park
Publications - 24
Citations - 770
Xinhui Zhou is an academic researcher from University of Maryland, College Park. The author has contributed to research in topics: Vocal tract & Formant. The author has an hindex of 11, co-authored 23 publications receiving 700 citations.
Papers
More filters
Journal ArticleDOI
A magnetic resonance imaging-based articulatory and acoustic study of "retroflex" and "bunched" American English /r/.
TL;DR: The results suggest that the F4/F5 differences between the variants can be largely explained by differences in whether the long cavity behind the palatal constriction acts as a half- or a quarter-wavelength resonator.
Proceedings ArticleDOI
Multicondition training of Gaussian PLDA models in i-vector space for noise and reverberation robust speaker recognition
TL;DR: A multicondition training strategy for Gaussian Probabilistic Linear Discriminant Analysis (PLDA) modeling of i-vector representations of speech utterances using a collection of individual subsystems tuned to specific conditions is presented.
Proceedings Article
Developing a Speech Activity Detection System for the DARPA RATS Program.
Tim Ng,Bing Zhang,Long Nguyen,Spyros Matsoukas,Xinhui Zhou,Nima Mesgarani,Karel Veselý,Pavel Matejka +7 more
TL;DR: It is shown that significant gains in SAD accuracy can be obtained by careful design of acoustic front end, feature normalization, incorporation of long span features via data-driven dimensionality reducing transforms, and channel dependent modeling.
Proceedings ArticleDOI
Linear versus mel frequency cepstral coefficients for speaker recognition
TL;DR: Comparing the performances between MFCC and LFCC in the NIST SRE (Speaker Recognition Evaluation) 2010 extended-core task shows that LFCC consistently outperforms MFCC, mainly due to its better performance in the female trials, and shows some advantage of LFCC over MFCC in reverberant speech.
Linear versus Mel Frequency Cepstral Coefficients for Speaker Recognition (Author's Manuscript)
TL;DR: In this article, the authors compared the performances between MFCC and LFCC (Linear frequency cepstral coefficients) in the NIST SRE (Speaker Recognition Evaluation) 2010 extended-core task.