AIConfPaper
← Search

Nirmesh J. Shah

4 accepted papers

2025

EmoReg: Directional Latent Vector Modeling for Emotional Intensity Regularization in Diffusion-based Voice Conversion

Ashishkumar Prabhakar Gudmalwar, Ishan Darshan Biyani, Nirmesh J. Shah, Pankaj Wasnik, Rajiv Ratn Shah
AAAI 2025technical

The Emotional Voice Conversion (EVC) aims to convert the discrete emotional state from the source emotion to the target for a given speech utterance while preserving linguistic content. In this paper, we propose regularizing emotion intensity in the diffusion-based EVC framework to generate precise…

Cited by 0Source ↗PDF ↗Scholar ↗
2017

Novel Amplitude Scaling method for bilinear frequency Warping-based Voice Conversion

Nirmesh J. Shah, Hemant A. Patil
ICASSP 2017accepted

In Frequency Warping (FW)-based Voice Conversion (VC), the source spectrum is modified to match the frequency-axis of the target spectrum followed by an Amplitude Scaling (AS) to compensate the amplitude differences between the warped spectrum and the actual target spectrum. In this paper, we propos…

Cited by 0Source ↗Scholar ↗
2017

Quality assessment of voice converted speech using articulatory features

Avni Rajpal, Nirmesh J. Shah, Mohammadi Zaki, Hemant A. Patil
ICASSP 2017accepted

We propose a novel application of the acoustic-to-articulatory inversion (AAI) towards a quality assessment of the voice converted speech. The ability of humans to speak effortlessly requires the coordinated movements of various articulators, muscles, etc. This effortless movement contributes toward…

Cited by 11Source ↗Scholar ↗