Cycle-consistent adversarial networks for non-parallel vocal effort based speaking style conversion

S Seshadri, L Juvela, J Yamagishi… - ICASSP 2019-2019 …, 2019 - ieeexplore.ieee.org
Speaking style conversion (SSC) is the technology of converting natural speech signals from
one style to another. In this study, we propose the use of cycle-consistent adversarial …

[HTML][HTML] Investigating a neural all pass warp in modern TTS applications

B Schnell, PN Garner - Speech Communication, 2022 - Elsevier
We present a neural implementation of the all pass warp (APW) previously used for vocal
tract length normalisation. This includes an efficient back-propagation, which can easily be …

Novel adaptive generative adversarial network for voice conversion

M Patel, M Parmar, S Doshi, NJ Shah… - 2019 Asia-Pacific …, 2019 - ieeexplore.ieee.org
Voice Conversion (VC) converts the speaking style of a source speaker to the speaking style
of a target speaker by preserving the linguistic content of a given speech utterance …

Novel inter mixture weighted GMM posteriorgram for DNN and GAN-based voice conversion

NJ Shah, R Sreeraj, N Shah… - 2018 Asia-Pacific Signal …, 2018 - ieeexplore.ieee.org
Voice Conversion (VC) requires an alignment of the spectral features before learning the
map** function, due to the speaking rate variations across the source and target speakers …

Novel metric learning for non-parallel voice conversion

NJ Shah, HA Patil - ICASSP 2019-2019 IEEE International …, 2019 - ieeexplore.ieee.org
Obtaining aligned spectral pairs in case of non-parallel data for stand-alone Voice
Conversion (VC) technique is a challenging research problem. Unsupervised alignment …

[PDF][PDF] Neural VTLN for speaker adaptation in TTS

B Schnell, PN Garner - Proc. 10th ISCA Speech Synth …, 2019 - publications.idiap.ch
Vocal tract length normalisation (VTLN) is well established as a speaker adaptation
technique that can work with very little adaptation data. It is also well known that VTLN can …

[PDF][PDF] Phone Aware Nearest Neighbor Technique Using Spectral Transition Measure for Non-Parallel Voice Conversion.

NJ Shah, HA Patil - INTERSPEECH, 2019 - researchgate.net
Nearest Neighbor (NN)-based alignment techniques are popular in non-parallel Voice
Conversion (VC). The performance of NN-based alignment improves with the information …

Mandarin-tibetan cross-lingual voice conversion system based on deep neural network

Z Gan, X ** perspective
NJ Shah - 2019 - 14.139.122.115
Understanding how a particular speaker is producing speech, and mimicking one's voice is
a difficult research problem due to the sophisticated mechanism involved in speech …

[PDF][PDF] Whether to pretrain DNN or not?: An empirical analysis for voice conversion

NJ Shah, HB Sailor, HA Patil - databases, 2019 - isca-archive.org
Abstract Recently, Deep Neural Network (DNN)-based Voice Conversion (VC) techniques
have become popular in the VC literature. These techniques suffer from the issue of …