Preprint Article Version 1 Preserved in Portico This version is not peer-reviewed

Performance Comparison of TTS Models for Brazilian Portuguese to Establish a Baseline

Version 1 : Received: 27 October 2022 / Approved: 1 November 2022 / Online: 1 November 2022 (04:37:04 CET)

A peer-reviewed article of this Preprint also exists.

W. Lobato, F. Farias, W. Cruz and M. Amadeus, "Performance Comparison of TTS Models for Brazilian Portuguese to Establish a Baseline," ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, 2023, pp. 1-5, doi: 10.1109/ICASSP49357.2023.10097264. W. Lobato, F. Farias, W. Cruz and M. Amadeus, "Performance Comparison of TTS Models for Brazilian Portuguese to Establish a Baseline," ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, 2023, pp. 1-5, doi: 10.1109/ICASSP49357.2023.10097264.

Abstract

This paper compares the performance of three text-to-speech (TTS) models released from June 2021 to January 2022 in order to establish a baseline for Brazilian Portuguese. Those models were trained using dataset for Brazilian Portuguese. The experimental setup considers tts-portuguese dataset to fine-tune the following TTS models: VITS end-to-end model; glowtts and gradtts acoustic models both using hifi-gan vocoder. Performance metrics are arranged into objective and subjective metrics. As subjective metrics, the naturalness and intelligibility are measured based on the mean opinion score (MOS). Results shows that gradtts+hifigan model achieved naturalness of 4.07 MOS, close to performance of current commercial models.

Keywords

text-to-speech; naturalness; intelligibility; Brazilian Portuguese

Subject

Computer Science and Mathematics, Computer Science

Comments (0)

We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.

Leave a public comment
Send a private comment to the author(s)
* All users must log in before leaving a comment
Views 0
Downloads 0
Comments 0
Metrics 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here.