R
Raghavendra Bilgi
Researcher at Amazon.com
Publications - 8
Citations - 26
Raghavendra Bilgi is an academic researcher from Amazon.com. The author has contributed to research in topics: Speaker recognition & Histogram equalization. The author has an hindex of 2, co-authored 7 publications receiving 24 citations. Previous affiliations of Raghavendra Bilgi include Indian Institute of Technology Madras.
Papers
More filters
Proceedings Article
Sub-Band Level Histogram Equalization for Robust Speech Recognition.
TL;DR: A novel modification of Histogram Equalization approach to robust speech recognition is described, known as Sub-band Histograms Equalization (S-HEQ), which has better equalization of the sub-bands as well as the overall cepstral histogram.
Proceedings Article
Efficient Speaker and Noise Normalization for Robust Speech Recognition.
TL;DR: The recently proposed T-VTLN approach to speaker normalization where matrix transformations are directly applied on cepstral features is investigated, showing that the speaker-specific warp-factors estimated even from noisy speech using this approach closely match those from clean-speech.
Proceedings ArticleDOI
Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-End
Swayambhu Nath Ray,Minhua Wu,Anirudh Raju,Pegah Ghahremani,Raghavendra Bilgi,Milind Rao,Harish Arsikere,Ariya Rastrow,Andreas Stolcke,Jasha Droppo +9 more
TL;DR: In this paper, an audio-to-intent (A2I) model encodes the intent of the utterance in the form of embeddings or posteriors, and these are used as auxiliary inputs for RNN-T training and inference.
Proceedings ArticleDOI
Noise and speaker compensation in the Log filter bank domain
TL;DR: The elegance of the proposed approach is that given the speech data, the authors obtain directly MFCC features that are robust to noise and speaker-variations that show a significant relative improvement over baseline on Aurora-4 task.
Proceedings ArticleDOI
Non-negative subspace projection during conventional MFCC feature extraction for noise robust speech recognition
TL;DR: An additional feature processing algorithm using Non-negative Matrix Factorization (NMF) is proposed to be included during the conventional extraction of Mel-frequency cepstral coefficients (MFCC) for achieving noise robustness in HMM based speech recognition.