Please use this identifier to cite or link to this item:
Title: Multi speaker text to speech transfer learning
Authors: Adra, Mira
Advisors: Mokbel, Chafic 
Keywords: Text to speech, Transfer learning, Multi-speaker, Tacotron 2, French
Subjects: Speech synthesis
Artificial intelligence
Automatic speech recognition
Machine learning
Dissertations, Academic
University of Balamand--Dissertations
Issue Date: 2023
Speech synthesis is experiencing a breakthrough as progressive leaps in artificial intelligence have led to a shift from the robotic standard voice to a more human-like voice with emotional inflections across multiple speakers and languages. Tacotron has been used intensively for such text-to-speech syntheses lately. Accordingly, in this thesis, I aim at studying the possibility of performing Multispeaker text-to-speech (TTS) transfer learning with Tacotron 2 in French to overcome the need of having multiple machines one per speaker. That is achieved by finetuning the Tacotron 2 training processor to allow learning the multiple speakers available in our dataset. For that, we use publicly available online French datasets that are already annotated. However, the main challenge that such models face is data efficiency and quality of the speaker audio files as well as speaker variability where each speaker might have a different accent or speaking rate. Despite that our model provided us with adequate results when presented with only a few hours of new speakers from different genders.
Includes bibliographical references (p. 35-36)
Rights: This object is protected by copyright, and is made available here for research and educational purposes. Permission to reuse, publish, or reproduce the object beyond the personal and educational use exceptions must be obtained from the copyright holder
Ezproxy URL: Link to full text
Type: Thesis
Appears in Collections:UOB Theses and Projects

Show full item record

Record view(s)

checked on Jun 15, 2024

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.