期刊
APPLIED ACOUSTICS
卷 210, 期 -, 页码 -出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.apacoust.2023.109425
关键词
Tacotron; WaveRNN; Speech synthesis; Text-to-speech; Emotional speech synthesis; Speech emotion recognition
类别
Despite the lack of speech emotion datasets, this paper suggests using synthetic emotional speech generated by an end-to-end text-to-speech (TTS) system to augment speech emotion recognition (SER) systems. The proposed TTS system includes encoders for speaker and emotion embeddings, a sequence-to-sequence text generator, and a WaveRNN for audio generation. Experimental results show that the generated emotional speech significantly improves SER performance on multiple datasets and effectively augments SER performance.
Despite advances in deep learning, current state-of-the-art speech emotion recognition (SER) systems still have poor performance due to a lack of speech emotion datasets. This paper proposes augmenting SER systems with synthetic emotional speech generated by an end-to-end text-to-speech (TTS) system based on an extended Tacotron 2 architecture. The proposed TTS system includes encoders for speaker and emotion embeddings, a sequence-to-sequence text generator for creating Mel-spectrograms, and a WaveRNN to generate audio from the Mel-spectrograms. Extensive experiments show that the quality of the generated emotional speech can significantly improve SER performance on multiple datasets, as demonstrated by a higher mean opinion score (MOS) compared to the baseline. The generated samples were also effective at augmenting SER performance.(c) 2023 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据