Log In Sign Up

Deep MOS Predictor for Synthetic Speech Using Cluster-Based Modeling

by   Yeunju Choi, et al.

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.


page 1

page 2

page 3

page 4


MOSNet: Deep Learning based Objective Assessment for Voice Conversion

Existing objective evaluation metrics for voice conversion (VC) are not ...

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

Developers of text-to-speech synthesizers (TTS) often make use of human ...

SpeechLMScore: Evaluating speech generation using speech language model

While human evaluation is the most reliable metric for evaluating speech...

Residual-Guided Non-Intrusive Speech Quality Assessment

This paper proposes an approach to improve Non-Intrusive speech quality ...

An Objective Evaluation Framework for Pathological Speech Synthesis

The development of pathological speech systems is currently hindered by ...

Improving pronunciation assessment via ordinal regression with anchored reference samples

Sentence level pronunciation assessment is important for Computer Assist...