ISCA Archive Interspeech 2021
ISCA Archive Interspeech 2021

An Attribute-Aligned Strategy for Learning Speech Representation

Yu-Lin Huang, Bo-Hao Su, Y.-W. Peter Hong, Chi-Chun Lee

Advancement in speech technology has brought convenience to our life. However, the concern is on the rise as speech signal contains multiple personal attributes, which would lead to either sensitive information leakage or bias toward decision. In this work, we propose an attribute-aligned learning strategy to derive speech representation that can flexibly address these issues by attribute-selection mechanism. Specifically, we propose a layered-representation variational autoencoder (LR-VAE), which factorizes speech representation into attribute-sensitive nodes, to derive an identity-free representation for speech emotion recognition (SER), and an emotionless representation for speaker verification (SV). Our proposed method achieves competitive performances on identity-free SER and a better performance on emotionless SV, comparing to the current state-of-the-art method of using adversarial learning applied on a large emotion corpora, the MSP-Podcast. Also, our proposed learning strategy reduces the model and training process needed to achieve multiple privacy-preserving tasks.

doi: 10.21437/Interspeech.2021-1341

Cite as: Huang, Y.-L., Su, B.-H., Hong, Y.-W.P., Lee, C.-C. (2021) An Attribute-Aligned Strategy for Learning Speech Representation. Proc. Interspeech 2021, 1179-1183, doi: 10.21437/Interspeech.2021-1341

  author={Yu-Lin Huang and Bo-Hao Su and Y.-W. Peter Hong and Chi-Chun Lee},
  title={{An Attribute-Aligned Strategy for Learning Speech Representation}},
  booktitle={Proc. Interspeech 2021},