Deep MOS Predictor for Synthetic Speech Using Cluster-Based Modeling

08/09/2020
by   Yeunju Choi, et al.
0

While deep learning has made impressive progress in speech synthesis and voice conversion, the assessment of the synthesized speech is still carried out by human participants. Several recent papers have proposed deep-learning-based assessment models and shown the potential to automate the speech quality assessment. To improve the previously proposed assessment model, MOSNet, we propose three models using cluster-based modeling methods: using a global quality token (GQT) layer, using an Encoding Layer, and using both of them. We perform experiments using the evaluation results of the Voice Conversion Challenge 2018 to predict the mean opinion score of synthesized speech and similarity score between synthesized speech and reference speech. The results show that the GQT layer helps to predict human assessment better by automatically learning the useful quality tokens for the task and that the Encoding Layer helps to utilize frame-level scores more precisely.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/17/2019

MOSNet: Deep Learning based Objective Assessment for Voice Conversion

Existing objective evaluation metrics for voice conversion (VC) are not ...
research
11/28/2016

AutoMOS: Learning a non-intrusive assessor of naturalness-of-speech

Developers of text-to-speech synthesizers (TTS) often make use of human ...
research
12/08/2022

SpeechLMScore: Evaluating speech generation using speech language model

While human evaluation is the most reliable metric for evaluating speech...
research
07/16/2020

Neural MOS Prediction for Synthesized Speech Using Multi-Task Learning With Spoofing Detection and Spoofing Type Classification

Several papers have proposed deep-learning-based models to predict the m...
research
10/18/2021

LDNet: Unified Listener Dependent Modeling in MOS Prediction for Synthetic Speech

An effective approach to automatically predict the subjective rating for...
research
03/22/2022

Residual-Guided Non-Intrusive Speech Quality Assessment

This paper proposes an approach to improve Non-Intrusive speech quality ...
research
07/06/2021

Location, Location: Enhancing the Evaluation of Text-to-Speech Synthesis Using the Rapid Prosody Transcription Paradigm

Text-to-Speech synthesis systems are generally evaluated using Mean Opin...

Please sign up or login with your details

Forgot password? Click here to reset