A
Anil Kumar Vuppala
Researcher at International Institute of Information Technology, Hyderabad
Publications - 107
Citations - 1069
Anil Kumar Vuppala is an academic researcher from International Institute of Information Technology, Hyderabad. The author has contributed to research in topics: Computer science & Language identification. The author has an hindex of 16, co-authored 95 publications receiving 875 citations. Previous affiliations of Anil Kumar Vuppala include International Institute of Information Technology & Indian Institute of Technology Kharagpur.
Papers
More filters
Journal ArticleDOI
Vowel Onset Point Detection for Low Bit Rate Coded Speech
TL;DR: The proposed VOP detection method has shown significant improvement in the performance compared to the existing method under clean as well as coded cases and is analyzed in CV recognition by using VOP as an anchor point.
Proceedings ArticleDOI
SFF Anti-Spoofer: IIIT-H Submission for Automatic Speaker Verification Spoofing and Countermeasures Challenge 2017.
K. N. R. K. Raju Alluri,Sivanand Achanta,Sudarsana Reddy Kadiri,Suryakanth V. Gangashetty,Anil Kumar Vuppala +4 more
TL;DR: The experimental results on ASVspoof 2017 dataset reveal that, SFF based representation is very effective in detecting replay attacks and the score level fusion of back end classifiers further improved the performance of the system which indicates that both classifiers capture complimentary information.
Proceedings ArticleDOI
IITKGP-MLILSC speech database for language identification
TL;DR: In this article, Gaussian mixture models (GMMs) are developed to capture the language specific information present in spectral features, and the performance of language identification system is analyzed in view of speaker dependent and independent cases.
Journal ArticleDOI
Improved vowel onset point detection using epoch intervals
TL;DR: In this paper, a two-level approach using multiple sources of evidence is proposed for the accurate detection of the onset point (VOP) in the speech signal, where at the first level, VOPs are identified by combining the complementary evidence from excitation source, spectral peaks and modulation spectrum.
Journal ArticleDOI
Non-uniform time scale modification using instants of significant excitation and vowel onset points
TL;DR: VOPs are determined using multiple sources of evidence from excitation source, spectral peaks, modulation spectrum and uniformity in epoch intervals, and instants of significant excitation are used to perform TSM as required.