Fusion of spectral and prosody modelling for multilingual speech emotion conversion

S Vekkot, D Gupta - Knowledge-Based Systems, 2022 - Elsevier
The paper proposes an integrated speech emotion conversion framework developed using
speaker-independent mixed-lingual training. The key contribution of the work is non-parallel …

Emotional voice conversion using a hybrid framework with speaker-adaptive DNN and particle-swarm-optimized neural network

S Vekkot, D Gupta, M Zakariah, YA Alotaibi - IEEE Access, 2020 - ieeexplore.ieee.org
We propose a hybrid network-based learning framework for speaker-adaptive vocal emotion
conversion, tested on three different datasets (languages), namely, EmoDB (German) …

Speaker-independent expressive voice synthesis using learning-based hybrid network model

S Vekkot, D Gupta - International Journal of Speech Technology, 2020 - Springer
Emotional voice conversion systems are used to formulate map** functions to transform
the neutral speech from output of text-to-speech systems to that of target emotion …

Hybrid framework for speaker-independent emotion conversion using i-vector PLDA and neural network

S Vekkot, D Gupta, M Zakariah, YA Alotaibi - IEEE Access, 2019 - ieeexplore.ieee.org
Expressive speech can be synthesized using acoustic feature modeling by map** the
spectral and fundamental frequency parameters between neutral speech and target …

Emotion Conversion in Telugu using Constrained Variance GMM and Continuous Wavelet Transform-

S Vekkot, D Gupta - TENCON 2019-2019 IEEE Region 10 …, 2019 - ieeexplore.ieee.org
Vocal emotion conversion forms a significant post-processing step in text-to-speech
synthesis. The existing models in emotion conversion are data intensive and …