paper-with-me

Papers

The VoiceMOS Challenge 2023: Zero-shot Subjective Speech Quality Prediction for Multiple Domains

2023-10-04 · Erica Cooper, Wen-Chin Huang, Yu Tsao, Hsin-Min Wang, Tomoki Toda, Junichi Yamagishi

We present the second edition of the VoiceMOS Challenge, a scientific event that aims to promote the study of automatic prediction of the mean opinion score (MOS) of synthesized and processed speech. This year, we emphasize real-world and challenging zero-shot out-of-domain MOS prediction with three tracks for three different voice evaluation scenarios. Ten teams from industry and academia in seven different countries participated. Surprisingly, we found that the two sub-tracks of French text-to-speech synthesis had large differences in their predictability, and that singing voice-converted samples were not as difficult to predict as we had expected. Use of diverse datasets and listener information during training appeared to be successful approaches.

📄 PDF Abstract BibTeX arXiv:2310.02640

Code (0)

등록된 구현이 없습니다.

Tasks

Speech Synthesistext-to-speechText to SpeechText-To-Speech Synthesis

Similar Papers 제목 키워드 기반

DDOS: A MOS Prediction Framework utilizing Domain Adaptive Pre-training and Distribution of Opinion Scores

2022-04-07 · Wei-Cheng Tseng, Wei-Tsung Kao, Hung-Yi Lee

Mean opinion score (MOS) is a typical subjective evaluation metric for speech synthesis systems. Since collecting MOS is time-consuming, it would be desirable if there are accurate MOS prediction models for automatic eva…

Self-Supervised LearningSpeech Synthesis

Using Rater and System Metadata to Explain Variance in the VoiceMOS Challenge 2022 Dataset

2022-09-14 · Michael Chinen, Jan Skoglund, Chandan K A Reddy, Alessandro Ragano 외

Non-reference speech quality models are important for a growing number of applications. The VoiceMOS 2022 challenge provided a dataset of synthetic voice conversion and text-to-speech samples with subjective labels. This…

text-to-speechText to SpeechVoice Conversion

The ZevoMOS entry to VoiceMOS Challenge 2022

2022-06-15 · Adriana Stan

This paper introduces the ZevoMOS entry to the main track of the VoiceMOS Challenge 2022. The ZevoMOS submission is based on a two-step finetuning of pretrained self-supervised learning (SSL) speech models. The first ste…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Self-Supervised Learningspeech-recognition+1

Quality Assessment of Noisy and Enhanced Speech with Limited Data: UWB-NTIS System for VoiceMOS 2024 and Beyond

2025-05-31 · Marie Kunešová

In this preprint, we present the UWB-NTIS-TTS team's submission to Track 3 of the VoiceMOS 2024 Challenge, the goal of which was to automatically assess the speech quality of noisy and de-noised speech in terms of the IT…

Prediction

A Study on Incorporating Whisper for Robust Speech Assessment

2023-09-22 · Ryandhimas E. Zezario, Yu-Wen Chen, Szu-Wei Fu, Yu Tsao 외

This research introduces an enhanced version of the multi-objective speech assessment model--MOSA-Net+, by leveraging the acoustic features from Whisper, a large-scaled weakly supervised model. We first investigate the e…

Self-Supervised Learning