Environment Sound Classification using Multiple Feature Channels and Attention based Deep Convolutional Neural Network
| Autor: | Jivitesh Sharma, Morten Goodwin, Ole-Christoffer Granmo |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Sound (cs.SD) Computer science 020209 energy Machine Learning (stat.ML) 02 engineering and technology computer.software_genre Convolutional neural network Computer Science - Sound Domain (software engineering) Machine Learning (cs.LG) Statistics - Machine Learning Audio and Speech Processing (eess.AS) 0202 electrical engineering electronic engineering information engineering FOS: Electrical engineering electronic engineering information engineering Audio signal processing VDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550 business.industry SIGNAL (programming language) Pattern recognition Feature (computer vision) Benchmark (computing) 020201 artificial intelligence & image processing Artificial intelligence Mel-frequency cepstrum business computer Electrical Engineering and Systems Science - Audio and Speech Processing Communication channel |
| Zdroj: | INTERSPEECH Interspeech |
| DOI: | 10.48550/arxiv.1908.11219 |
| Popis: | In this paper, we propose a model for the Environment Sound Classification Task (ESC) that consists of multiple feature channels given as input to a Deep Convolutional Neural Network (CNN) with Attention mechanism. The novelty of the paper lies in using multiple feature channels consisting of Mel-Frequency Cepstral Coefficients (MFCC), Gammatone Frequency Cepstral Coefficients (GFCC), the Constant Q-transform (CQT) and Chromagram. Such multiple features have never been used before for signal or audio processing. And, we employ a deeper CNN (DCNN) compared to previous models, consisting of spatially separable convolutions working on time and feature domain separately. Alongside, we use attention modules that perform channel and spatial attention together. We use some data augmentation techniques to further boost performance. Our model is able to achieve state-of-the-art performance on all three benchmark environment sound classification datasets, i.e. the UrbanSound8K (97.52%), ESC-10 (95.75%) and ESC-50 (88.50%). To the best of our knowledge, this is the first time that a single environment sound classification model is able to achieve state-of-the-art results on all three datasets. For ESC-10 and ESC-50 datasets, the accuracy achieved by the proposed model is beyond human accuracy of 95.7% and 81.3% respectively. Comment: Re-checking results |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|