arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2206.07448eess.AS
收藏

ZevoMOS参加2022年VoiceMOS挑战赛

The ZevoMOS entry to VoiceMOS Challenge 2022

Adriana Stan

摘要:

本文介绍了ZevoMOS进入2022年VoiceMOS挑战赛主赛道的情况。ZevoMOS的提交是基于预训练的自监督学习(SSL)语音模型的两步微调。第一步的任务是对自然语音和合成语音进行分类,而第二步的任务是预测与每个训练样本相关联的MOS分数。然后将微调过程的结果与从自动语音识别模型中提取的置信度分数以及从wav2vec SSL语音模型中获得的训练样本的原始嵌入相结合。在VoiceMOS挑战中分配给ZevoMOS系统的团队ID为T01。该提交物在系统级SRCC中排名第14位,在话语级MSE中排名第9位。本文还介绍了额外的评价的中间结果。

英文摘要:

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 step uses a task of classifying natural versus synthetic speech, while the second step's task is to predict the MOS scores associated with each training sample. The results of the finetuning process are then combined with the confidence scores extracted from an automatic speech recognition model, as well as the raw embeddings of the training samples obtained from a wav2vec SSL speech model. The team id assigned to the ZevoMOS system within the VoiceMOS Challenge is T01. The submission was placed on the 14th place with respect to the system-level SRCC, and on the 9th place with respect to the utterance-level MSE. The paper also introduces additional evaluations of the intermediate results.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑