Saved in:
Bibliographic Details
Main Authors: Agrawal, Saurabh, Gohil, Raj, Agrawal, Gopal Kumar, M, Vikram C, Verma, Kushal
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.02082
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909634634186752
author Agrawal, Saurabh
Gohil, Raj
Agrawal, Gopal Kumar
M, Vikram C
Verma, Kushal
author_facet Agrawal, Saurabh
Gohil, Raj
Agrawal, Gopal Kumar
M, Vikram C
Verma, Kushal
contents Speech quality assessment is a critical process in selecting text-to-speech synthesis (TTS) or voice conversion models. Evaluation of voice synthesis can be done using objective metrics or subjective metrics. Although there are many objective metrics like the Perceptual Evaluation of Speech Quality (PESQ), Perceptual Objective Listening Quality Assessment (POLQA) or Short-Time Objective Intelligibility (STOI) but none of them is feasible in selecting the best model. On the other hand subjective metric like Mean Opinion Score is highly reliable but it requires a lot of manual efforts and are time-consuming. To counter the issues in MOS Evaluation, we have developed a novel model, Speaker Agnostic Latent Features (SALF)-Mean Opinion Score (MOS) which is a small-sized, end-to-end, highly generalized and scalable model for predicting MOS score on a scale of 5. We use the sequences of convolutions and stack them to get the latent features of the audio samples to get the best state-of-the-art results based on mean squared error (MSE), Linear Concordance Correlation coefficient (LCC), Spearman Rank Correlation Coefficient (SRCC) and Kendall Rank Correlation Coefficient (KTAU).
format Preprint
id arxiv_https___arxiv_org_abs_2506_02082
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SALF-MOS: Speaker Agnostic Latent Features Downsampled for MOS Prediction
Agrawal, Saurabh
Gohil, Raj
Agrawal, Gopal Kumar
M, Vikram C
Verma, Kushal
Sound
Artificial Intelligence
Machine Learning
Speech quality assessment is a critical process in selecting text-to-speech synthesis (TTS) or voice conversion models. Evaluation of voice synthesis can be done using objective metrics or subjective metrics. Although there are many objective metrics like the Perceptual Evaluation of Speech Quality (PESQ), Perceptual Objective Listening Quality Assessment (POLQA) or Short-Time Objective Intelligibility (STOI) but none of them is feasible in selecting the best model. On the other hand subjective metric like Mean Opinion Score is highly reliable but it requires a lot of manual efforts and are time-consuming. To counter the issues in MOS Evaluation, we have developed a novel model, Speaker Agnostic Latent Features (SALF)-Mean Opinion Score (MOS) which is a small-sized, end-to-end, highly generalized and scalable model for predicting MOS score on a scale of 5. We use the sequences of convolutions and stack them to get the latent features of the audio samples to get the best state-of-the-art results based on mean squared error (MSE), Linear Concordance Correlation coefficient (LCC), Spearman Rank Correlation Coefficient (SRCC) and Kendall Rank Correlation Coefficient (KTAU).
title SALF-MOS: Speaker Agnostic Latent Features Downsampled for MOS Prediction
topic Sound
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2506.02082