Follow
Mahsa Elyasi
Mahsa Elyasi
Research Scientist at The AI Foundation
Verified email at aifoundation.com - Homepage
Title
Cited by
Cited by
Year
Generalized spoofing detection inspired from audio generation artifacts
Y Gao, T Vuong, M Elyasi, G Bharaj, R Singh
arXiv preprint arXiv:2104.04111, 2021
192021
The effect of phase information in speech enhancement and speech recognition
MS Elyasi Langarani, H Veisi, H Sameti
Information Science, Signal Processing and their Applications (ISSPA), 2012 …, 2012
11*2012
A novel pitch decomposition method for the generalized linear alignment model
MS Elyasi Langarani, E Klabbers, J Van Santen
Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International …, 2014
10*2014
Modeling fundamental frequency dynamics in hypokinetic dysarthria
MS Elyasi Langarani, J Van Santen
Spoken Language Technology Workshop (SLT), 2014 IEEE, 272-276, 2014
9*2014
Data-driven Foot-based Intonation Generator for Text-to-Speech Synthesis
MSE Langarani, J van Santen, SH Mohammadi, A Kain
Interspeech, 2015
62015
SPEAKER INTONATION ADAPTATION FOR TRANSFORMING TEXT-TO-SPEECH SYNTHESIS SPEAKER IDENTITY
MS Elyasi Langarani, J van Santen
4*2015
Flavored tacotron: Conditional learning for prosodic-linguistic features
M Elyasi, G Bharaj
arXiv preprint arXiv:2104.04050, 2021
32021
KNNDIST: A Non-Parametric Distance Measure for Speaker Segmentation.
SH Mohammadi, H Sameti, MS Elyasi Langarani, A Tavanaei
INTERSPEECH, 2282-2285, 2012
22012
A Generalized Model for Analysis and Synthesis of English Intonation: A Dissertation
MSE Langarani
Oregon Health & Science University, 2020
2020
Recurrent convolutional networks for classification of speaker groups based on prosodic information
MS Elyasi Langarani, J van Santen
Women in Machine Learning, WiML, 2017
2017
Foot-based intonation for text-to-speech synthesis using neural networks
MSE Langarani, J van Santen
Proceedings of the International Conference on Speech Prosody 2016, 1009-1013, 2016
2016
Automatic, model-based detection of pause-less phrase boundaries from fundamental frequency and duration features.
MSE Langarani, JPH van Santen
SSW, 1-6, 2016
2016
The system can't perform the operation now. Try again later.
Articles 1–12