Speech Enhancement Model Synthesis Based on Federal Learning for Industrial CPS in Multiple Noise Conditions
Open Access
Abstract
Real-time acquisition of industrial production data and rapid response to changes in the external environment are key to ensuring the symmetry of a CPS. However, during industrial production, the collected data are inevitably disturbed by environmental noise, which has a huge impact on the subsequent data processing of a CPS. The types of noise vary greatly in different work scenarios in a factory. Meanwhile, barriers such as data privacy protection and copyright restrictions create great difficulties for model synthesis in the information space. A speech enhancement model with teacher–student architecture based on federal knowledge distillation is proposed to alleviate this problem. (1) We pre-train teacher models under different noise conditions to create multiple teacher models with symmetry and excelling in the suppression of a priori noise. (2) We construct a symmetric model–student model of the physical space of the teacher model trained on public data and transfer the knowledge of the teacher model to the student model. The student model can suppress multiple types of noise. Notably, with the TIMIT dataset and the NoiseX92 noise set, the accuracy of the proposed method improved by an average of over the randomly specified teacher method in the PESQ metric and for STOI.
Keywords
Funding Information
- National Key R&D Program of China (2021YFB1715000)
- Sichuan Science and Technology Program (2021YFG0315)
This publication has 41 references indexed in Scilit:
- Complex Ratio Masking for Monaural Speech SeparationIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2015
- Cyber-physical systems: A security perspective2015
- Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks2015
- The voice bank corpus: Design, collection and data analysis of a large regional accent speech database2013
- The importance of phase in speech enhancementSpeech Communication, 2011
- A signal subspace approach for speech enhancementIEEE Transactions on Speech and Audio Processing, 1995
- Assessment for automatic speech recognition: II. NOISEX-92: A database and an experiment to study the effect of additive noise on speech recognition systemsSpeech Communication, 1993
- Speech enhancement using a minimum mean-square error log-spectral amplitude estimatorIEEE Transactions on Acoustics, Speech, and Signal Processing, 1985
- Suppression of acoustic noise in speech using spectral subtractionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1979
- All-pole modeling of degraded speechIEEE Transactions on Acoustics, Speech, and Signal Processing, 1978