Acoustic scene classification using teacher-student learning with soft-labels

Abstract

Acoustic scene classification identifies an input segment into one of the pre-defined classes using spectral information. The spectral information of acoustic scenes may not be mutually exclusive due to common acoustic properties across different classes, such as babble noises included in both airports and shopping malls. However, conventional training procedure based on one-hot labels does not consider the similarities between different acoustic scenes. We exploit teacher-student learning with the purpose to derive soft-labels that consider common acoustic properties among different acoustic scenes. In teacher-student learning, the teacher network produces soft-labels, based on which the student network is trained. We investigate various methods to extract soft-labels that better represent similarities across different scenes. Such attempts include extracting soft-labels from multiple audio segments that are defined as an identical acoustic scene. Experimental results demonstrate the potential of our approach, showing a classification accuracy of 77.36 % on the DCASE 2018 task 1 validation set.

Accepted for presentation at Interspeech 2019

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Distilling the Knowledge in a Neural Network
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• On Calibration of Modern Neural Networks
• A multi-device dataset for urban acoustic scene classification
• Convolutional Neural Networks and x-vector Embedding for DCASE2018 Acoustic Scene Classification Challenge
• Short utterance compensation in speaker verification via cosine-based teacher-student learning of speaker embeddings

Cited by in corpus (5)

• Sound Context Classification Basing on Join Learning Model and Multi-Spectrogram Features
• Relational Teacher Student Learning with Neural Label Embedding for Device Adaptation in Acoustic Scene Classification
• Sound Event Detection by Multitask Learning of Sound Events and Scenes with Soft Scene Labels
• Capturing scattered discriminative information using a deep architecture in acoustic scene classification
• Intra-Utterance Similarity Preserving Knowledge Distillation for Audio Tagging