1 |
Investigating deep neural structures and their interpretability in the domain of voice conversion
|
|
|
|
Abstract:
Generative Adversarial Networks (GANs) are machine learning networks based around creating synthetic data. Voice Conversion (VC) is a subset of voice translation that involves translating the paralinguistic features of a source speaker to a target speaker while preserving the linguistic information. The aim of non-parallel conditional GANs for VC is to translate an acoustic speech feature sequence from one domain to another without the use of paired data. In the study reported here, we investigated the interpretability of state-of-the-art implementations of non-parallel GANs in the domain of VC. We show that the learned representations in the repeating layers of a particular GAN architecture remain close to their original random initialised parameters, demonstrating that it is the number of repeating layers that is more responsible for the quality of the output. We also analysed the learned representations of a model trained on one particular dataset when used during transfer learning on another dataset. This also showed high levels of similarity in the repeating layers. Together, these results provide new insight into how the learned representations of deep generative networks change during learning and the importance of the number of layers, which would help build better GAN-based speech conversion models.
|
|
URL: https://eprints.whiterose.ac.uk/180841/1/Broughton%20-%20Investigating%20Deep%20Neural%20Structures%20and%20their%20Interpretability%20in%20the%20Domain%20of%20Voice%20Conversion.pdf https://www.isca-speech.org/archive/interspeech_2021/broughton21_interspeech.html https://eprints.whiterose.ac.uk/180841/
|
|
BASE
|
|
Hide details
|
|
2 |
A Very Low Resource Language Speech Corpus for Computational Language Documentation Experiments
|
|
|
|
In: Language Resources and Evaluation Conference (LREC) ; https://hal.archives-ouvertes.fr/hal-01807093 ; Language Resources and Evaluation Conference (LREC), Nicoletta Calzolari (Conference chair) and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Koiti Hasida and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and Hélène Mazo and Asuncion Moreno and Jan Odijk and Stelios Pi, May 2018, Miyazaki, Japan (2018)
|
|
BASE
|
|
Show details
|
|
5 |
A Very Low Resource Language Speech Corpus for Computational Language Documentation Experiments ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Ressources pour l'apprentissage, le développement et l'évaluation des systêmes de dictée vocale en français : corpus de texte, de parole et lexical
|
|
|
|
In: http://infoscience.epfl.ch/record/97977 (2006)
|
|
BASE
|
|
Show details
|
|
|
|