On the impact of normalization strategies in unsupervised adversarial domain adaptation for acoustic scene classification

Michel Olvera (1) , Emmanuel Vincent (1) , Gilles Gasso (2)

1 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication
2 LITIS - Laboratoire d'Informatique, du Traitement de l'Information et des Systèmes

Acoustic scene classification systems face performance degradation when trained and tested on data recorded by different devices. Unsupervised domain adaptation methods have been studied to reduce the impact of this mismatch. While they do not assume the availability of labels at test time, they often exploit parallel data recorded by both devices, and thus are not fully blind to the target domain. In this paper, we address a more practical scenario where parallel data are not available. We thoroughly analyze the impact of normalization and moment matching strategies to compensate for the linear distortion introduced by the recording device and propose their integration with adversarial domain adaptation to handle the remaining non-linear distortion. Experiments on the DCASE Challenge 2018 Task 1B dataset show that the proposed integrated approach considerably reduces domain mismatch, reaching an accuracy in the target domain close to that obtained in the source domain.

Mots clés: Acoustic scene classification; adversarial domain adaptation; feature normalization; moment matching

Domaines: Traitement du signal et de l'image [eess.SP]

Michel Olvera, Emmanuel Vincent, Gilles Gasso. On the impact of normalization strategies in unsupervised adversarial domain adaptation for acoustic scene classification. ICASSP 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing, May 2022, Singapore, Singapore. ⟨10.1109/ICASSP43922.2022.9747540⟩. ⟨hal-03668251⟩