MOSNet: Deep Learning based Objective Assessment for Voice Conversion (2019-04-17T00:00:00.000000Z)

TL;DR

Results confirm that the proposed deep learning-based assessment models could be used as a computational evaluator to measure the MOS of VC systems to reduce the need for expensive human rating.

Abstract

Existing objective evaluation metrics for voice conversion (VC) are not always correlated with human perception. Therefore, training VC models with such criteria may not effectively improve naturalness and similarity of converted speech. In this paper, we propose deep learning-based assessment models to predict human ratings of converted speech. We adopt the convolutional and recurrent neural network models to build a mean opinion score (MOS) predictor, termed as MOSNet. The proposed models are tested on large-scale listening test results of the Voice Conversion Challenge (VCC) 2018. Experimental results show that the predicted scores of the proposed MOSNet are highly correlated with human MOS ratings at the system level while being fairly correlated with human MOS ratings at the utterance level. Meanwhile, we have modified MOSNet to predict the similarity scores, and the preliminary results show that the predicted scores are also fairly correlated with human ratings. These results confirm that the proposed models could be used as a computational evaluator to measure the MOS of VC systems to reduce the need for expensive human rating.

Authors

Xin Wang

8 papers

J. Yamagishi

12 papers

Szu-Wei Fu

4 papers

MOSNet: Deep Learning based Objective Assessment for Voice Conversion

TL;DR

Abstract

Authors

References25 items

Non-intrusive Speech Quality Assessment Using Neural Networks

A Convolutional Recurrent Neural Network for Real-Time Speech Enhancement

Temporal Attentive Pooling for Acoustic Event Detection

Quality-Net: An End-to-End Non-intrusive Speech Quality Assessment Model based on BLSTM

Gated Convolutional LSTM for Speech Commands Recognition

Convolutional-Recurrent Neural Networks for Speech Enhancement

The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methods

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

A Hierarchical Predictor of Synthetic Speech Naturalness Using Neural Networks

Convolutional, Long Short-Term Memory, fully connected Deep Neural Networks

The proof and measurement of association between two things.

Can we Automatically Transform Speech Recorded on Common Consumer Devices in Real-World Environments into Professional Production Quality Speech?—A Dataset, Insights, and Challenges

Adam: A Method for Stochastic Optimization

Rectified Linear Units Improve Restricted Boltzmann Machines

Single-Ended Speech Quality Measurement Using Machine Learning Methods

Bootstrap estimates for confidence intervals in ASR performance evaluation

Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs

Mel-cepstral distance measure for objective speech quality assessment

NOTES ON THE HISTORY OF CORRELATION

Learning the speech front-end with raw waveform CLDNNs

Dropout: a simple way to prevent neural networks from overfitting

Objective evaluation measures for speaker-adaptive HMM-TTS systems

Prediction of Perceived Sound Quality of Synthetic Speech

An Introduction to the Bootstrap

An Evaluation of Synthetic Speech Using the PESQ Measure

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names