arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.15032eess.AS
收藏

基于Wav2Vec 2.0的语音韵律边界检测

Detection of Prosodic Boundaries in Speech Using Wav2Vec 2.0

Marie Kunešová, Markéta Řezáčková

摘要:

语音中的韵律边界对语音合成和音频标注都有重要意义。在本文中,我们应用wav2vec 2.0框架的任务检测这些边界的语音信号,只使用声学信息。我们测试了一组录音的捷克广播新闻,由语音专家标记的方法,并将其与现有的基于文本的预测,它使用相同的数据的成绩单。尽管使用了相对少量的标记数据,wav2vec2模型在句子内韵律边界上实现了94%的准确度和83%的F1测量(或在所有韵律边界上实现了95%和89%),优于基于文本的方法。然而,通过结合两个不同模型的输出,我们可以进一步改善结果。

英文摘要:

Prosodic boundaries in speech are of great relevance to both speech synthesis and audio annotation. In this paper, we apply the wav2vec 2.0 framework to the task of detecting these boundaries in speech signal, using only acoustic information. We test the approach on a set of recordings of Czech broadcast news, labeled by phonetic experts, and compare it to an existing text-based predictor, which uses the transcripts of the same data. Despite using a relatively small amount of labeled data, the wav2vec2 model achieves an accuracy of 94% and F1 measure of 83% on within-sentence prosodic boundaries (or 95% and 89% on all prosodic boundaries), outperforming the text-based approach. However, by combining the outputs of the two different models we can improve the results even further.

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。

↑