Implementation of a multispeaker text-to-speech synthesis on a server
Akhmetzhanov, Nursultan (2021)
Akhmetzhanov, Nursultan
2021
All rights reserved. This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:amk-2021052812170
https://urn.fi/URN:NBN:fi:amk-2021052812170
Tiivistelmä
The main goal of this thesis was to implement a multispeaker model on a web application, additional goals were to introduce the reader to text-to-speech synthesis and compare the open source multispeaker models.
Most of the information was taken from the original research papers and used to explain the work of the models and compare the models of multispeaker TTS using the MOS (Mean Opinion Score) values from the papers themselves. The development of the web application with multispeaker TTS functionality was based on open-source repositories for TTS.
As a result, the goal was not met due to the complexity of the chosen task, lack of knowledge and experience in deep learning and speech synthesis. The steps in the development of the practical application and the recommendations on how to proceed with the tasks were written and explained.
Most of the information was taken from the original research papers and used to explain the work of the models and compare the models of multispeaker TTS using the MOS (Mean Opinion Score) values from the papers themselves. The development of the web application with multispeaker TTS functionality was based on open-source repositories for TTS.
As a result, the goal was not met due to the complexity of the chosen task, lack of knowledge and experience in deep learning and speech synthesis. The steps in the development of the practical application and the recommendations on how to proceed with the tasks were written and explained.
Kokoelmat
Samankaltainen aineisto
Näytetään aineisto, joilla on samankaltaisia nimekkeitä, tekijöitä tai asiasanoja.
-
Speech synthesis : Developing a web application implementing speech technology
Gebremariam, Gudeta (Metropolia Ammattikorkeakoulu, 2016)Speech is a natural media of communication for humans. Text-to-speech (TTS) technology uses a computer to synthesize speech. There are three main techniques of TTS synthesis. These are formant-based, articulatory and ... -
Speech and Language difficulties : An assessment of the parents experiences who have children with speech and language difficulties and services provided in northern part of Finland
Kilpeläinen, Faith (Kemi-Tornion ammattikorkeakouluLapin ammattikorkeakoulu, 2012)Degree Program: Bachelor of social services Author Faith Kilpeläinen Thesis title: Speech and language difficulties Pages 56 Date: 05.10.12 Thesis instructor(s): Leppälä Sari & Vinkki Kaisu Thesis Description. ... -
Google Speech -rajapinta mobiilisovelluksessa
Kallio, Eetu (2019)Tämän opinnäytetyön tavoitteena oli perehtyä Google Speech -rajapintaan ja sen tuomiin mahdollisuuksiin alustariippumattomissa mobiilisovelluksissa. Lisäksi haluttiin selvittää, onko rajapinta yhteensopiva toimeksiantaja ...