Relational Teacher Student Learning with Neural Label Embedding for Device Adaptation in Acoustic Scene Classification

Abstract

In this paper, we propose a domain adaptation framework to address the device mismatch issue in acoustic scene classification leveraging upon neural label embedding (NLE) and relational teacher student learning (RTSL). Taking into account the structural relationships between acoustic scene classes, our proposed framework captures such relationships which are intrinsically device-independent. In the training stage, transferable knowledge is condensed in NLE from the source domain. Next in the adaptation stage, a novel RTSL strategy is adopted to learn adapted target models without using paired source-target data often required in conventional teacher student learning. The proposed framework is evaluated on the DCASE 2018 Task1b data set. Experimental results based on AlexNet-L deep classification models confirm the effectiveness of our proposed approach for mismatch situations. NLE-alone adaptation compares favourably with the conventional device adaptation and teacher student based adaptation techniques. NLE with RTSL further improves the classification accuracy.

Accepted by Interspeech 2020

References in corpus (10)

• Distilling the Knowledge in a Neural Network
• A multi-device dataset for urban acoustic scene classification
• Integrating the Data Augmentation Scheme with Various Classifiers for Acoustic Scene Modeling
• Device-Robust Acoustic Scene Classification Based on Two-Stage Categorization and Data Augmentation
• Convolutional Neural Networks and x-vector Embedding for DCASE2018 Acoustic Scene Classification Challenge
• Unsupervised adversarial domain adaptation for acoustic scene classification
• Acoustic scene classification using convolutional neural network and multiple-width frequency-delta data augmentation
• Large-Scale Domain Adaptation via Teacher-Student Learning
• Acoustic Scene Classification by Implicitly Identifying Distinct Sound Events
• Acoustic scene classification using teacher-student learning with soft-labels

Cited by in corpus (2)

• REDAT: Accent-Invariant Representation for End-to-End ASR by Domain Adversarial Training with Relabeling
• Adversarial Domain Adaptation with Paired Examples for Acoustic Scene Classification on Different Recording Devices