Thesis Title: “Statistical Methods for Speech Processing In Low Resource Environments”
Seminar Abstract: “Statistical Methods for Speech Processing In Low Resource Environments”
Seminar Presentation: “Statistical Methods for Speech Processing In Low Resource Environments”
Co-superviser: Prof. Koby Crammer
Thesis Related Publications:
- H. Benisty, I. Katz, K. Crammer and D. Malah, “Discriminative Keyword Spotting for Limited-Data Applications“, Speech Communication, Vol. 99, 2018, pp-1–11
- H. Benisty, D. Malah, and K. Crammer, “Grid-based approximation for voice conversion in low resource environments“, EURASIP Journal on Audio, Speech, and Music Processing (2016)
- H. Benisty, D. Malah, and K. Crammer, “Sequential Voice Conversion Using Grid-Based Approximation“, 2014 IEEE 28-th Convention of Electrical and Electronics Engineers in Eilat, Israel, Dec. 3-6, 2014. Presentation
[Best student paper award] (Expanded version in: CCIT Report #843 Nov. 2013) - H. Benisty, D. Malah, and K. Crammer,”Non-Parallel Voice Conversion Using Join Optimization of Alignment by Temporal Context and Spectral Distortion“. ICASSP-2014, Florence, Italy, May 2014. Poster
- H. Benisty, D. Malah, and K. Crammer,”Modular Global Variance Enhancement for Voice Conversion Systems“, 20th European Signal Processing Conference, EUSIPCO-2012, Bucharest, Romania, Aug. 27-31, 2012. Poster
- H. Benisty and D. Malah, “Voice Conversion using GMM with Enhanced Global Variance“, Interspeech-2011, Florence, Italy, Aug. 2011. Presentation