Novel TEO-based Gammatone features for environmental sound classification

In this paper, we propose to use modified Gammatone filterbank with Teager Energy Operator (TEO) for environmental sound classification (ESC) task. TEO can track energy as a function of both amplitude and frequency of an audio signal. TEO is better for capturing energy variations in the signal that is produced by a real physical system, such as, environmental sounds that contain amplitude and frequency modulations. In proposed feature set, we have used Gammatone filterbank since it represents characteristics of human auditory processing. Here, we have used two classifiers, namely, Gaussian Mixture Model (GMM) using cepstral features, and Convolutional Neural Network (CNN) using spectral features. We performed experiments on two datasets, namely, ESC-50, and UrbanSound8K. We compared TEO-based coefficients with Mel filter cepstral coefficients (MFCC) and Gammatone cepstral coefficients (GTCC), in which GTCC used mean square energy. Using GMM, the proposed TEO-based Gammatone Cepstral Coefficients (TEO-GTCC), and its score-level fusion with MFCC gave absolute improvement of 0.45 %, and 3.85 % in classification accuracy over MFCC on ESC-50 dataset. Similarly, on UrbanSound8K dataset the proposed TEO-GTCC, and its score-level fusion with GTCC gave absolute improvement of 1.40 %, and 2.44 % in classification accuracy over MFCC. Using CNN, the score-level fusion of Gammatone spectral coefficient (GTSC) and the proposed TEO-based Gammatone spectral coefficients (TEO-GTSC) gave absolute improvement of 14.10 %, and 14.52 % in classification accuracy over Mel filterbank energies (FBE) on ESC-50 and UrbanSond8K datasets, respectively. This shows that proposed TEO-based Gammatone features contain complementary information which is helpful in ESC task.

• Publication year

  2017

• Venue

  European Signal Processing Conference

• Publication date

  2017-08-01

• Fields of study

  Computer Science, Engineering, Environmental Science

• Identifiers
  DOI 10.23919/EUSIPCO.2017.8081521
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification

  2016cited by this paper
• Detection of overlapping acoustic events using a temporally-constrained probabilistic model

  2016cited by this paper
• Acoustic scene classification with matrix factorization for unsupervised feature learning

  2016cited by this paper
• Audio Surveillance of Roads: A System for Detecting Anomalous Sounds

  2016cited by this paper
• ESC: Dataset for Environmental Sound Classification

  2015influential reference
• Unsupervised feature learning for urban sound classification

  2015cited by this paper
• Sound event detection in real life recordings using coupled matrix factorization of spectral representations and class activity annotations

  2015cited by this paper
• Environmental sound classification with convolutional neural networks

  2015influential reference
• Acoustic Scene Classification

  2015cited by this paper
• Improving event detection for audio surveillance using Gabor filterbank features

  2015cited by this paper
• Polyphonic sound event detection using multi label deep neural networks

  2015cited by this paper
• Acoustic Scene Classification: Classifying environments from the sounds they produce

  2014cited by this paper
• A Dataset and Taxonomy for Urban Sound Research

  2014influential reference
• An Overview of Noise-Robust Automatic Speech Recognition

  2014cited by this paper
• Recent advances in deep learning for speech research at Microsoft

  2013cited by this paper
• Detection and classification of acoustic scenes and events: An IEEE AASP challenge

  2013cited by this paper
• Gammatone Cepstral Coefficients: Biologically Inspired Features for Non-Speech Audio Classification

  2012influential reference
• Time–Frequency Matrix Feature Extraction and Classification of Environmental Audio Signals

  2011cited by this paper
• Environmental Sound Recognition With Time–Frequency Audio Features

  2009cited by this paper
• An auditory-based feature for robust speech recognition

  2009cited by this paper
• Deep networks for audio event classification in soccer videos

  2009cited by this paper
• A computational model of human auditory signal processing and perception.

  2008cited by this paper
• The bag-of-frames approach to audio pattern recognition: a sufficient model for urban soundscapes but not for polyphonic music.

  2007cited by this paper
• Feature Selection for Sound Classification in Hearing Aids Through Restricted Search Driven by Genetic Algorithms

  2007cited by this paper
• Sound Classification in a Smart Room Environment: an Approach using GMM and HMM Methods

  2007cited by this paper
• Gammatone Features and Feature Combination for Large Vocabulary Speech Recognition

  2007cited by this paper
• Concurrent encoding of frequency and amplitude modulation in human auditory cortex: MEG evidence.

  2006influential reference
• Auditory Teager energy cepstrum coefficients for robust speech recognition

  2005cited by this paper
• On amplitude and frequency demodulation using energy operators

  1993cited by this paper
• Evidence for Nonlinear Sound Production Mechanisms in the Vocal Tract

  1990cited by this paper
• Derivation of auditory filter shapes from notched-noise data.

  1990cited by this paper
• A cochlear frequency-position function for several species--29 years later.

  1990cited by this paper
• On a simple algorithm to calculate the 'energy' of a signal

  1990cited by this paper
• Speaker-independent phone recognition using hidden Markov models

  1989influential reference
• Temporal coding of resonances by low-frequency auditory nerve fibers: single-fiber responses and a population model.

  1988cited by this paper

• Adaptive threshold in Leaky-Integrated-and-Fire function for audio-based industrial diagnosis

  2025cites this paper
• EfficientAudioNet: Enhancing Environmental Sound Classification through Data Fusion of Multiple Audio Representations

  2025cites this paper
• YAMNet-based transfer learning for compact noise classification in urban and wireless systems

  2025cites this paper
• Utilizing gammatone filter coefficient to improve human mouth-click signal detection using a multi-phase correlation process

  2024cites this paper
• Environment Sound Classification using stacked features and convolutional neural network

  2024cites this paper
• Overheard: Audio-based Integral Event Inference

  2024cites this paper
• Studying the Effect of Audio Filters in Pre-Trained Models for Environmental Sound Classification

  2024cites this paper
• Deep learning vs feature engineering in the assessment of voice signals for diagnosis in Parkinson’s disease

  2023cites this paper
• Failure Detection from the Knocking Sounds Using Convolutional Neural Network

  2023cites this paper
• EnViTSA: Ensemble of Vision Transformer with SpecAugment for Acoustic Event Classification

  2023influential citation
• Low-Complexity Environmental Sound Classification using Cadence Frequency Diagram and Chebychev Moments

  2023cites this paper
• Acoustic scene classification: A comprehensive survey

  2023cites this paper
• MSARN: A Multi-scale Attention Residual Network for End-to-End Environmental Sound Classification

  2023influential citation
• A Deep Learning-Based Coyote Detection System Using Audio Data

  2023cites this paper
• A Machine Learning-Based Approach for Audio Signals Classification using Chebychev Moments and Mel-Coefficients

  2022cites this paper
• Environmental Sound Classification Based on Transfer-Learning Techniques with Multiple Optimizers

  2022cites this paper
• An Approach for Audio-Visual Content Understanding of Video using Multimodal Deep Learning Methodology

  2022cites this paper
• Environmental Sound Classification via Time–Frequency Attention and Framewise Self-Attention-Based Deep Neural Networks

  2022cites this paper
• Indoor Event Detection with Sound Data

  2021cites this paper
• Spectral images based environmental sound classification using CNN with meaningful data augmentation

  2021cites this paper
• Semantic feature extraction based on subspace learning with temporal constraints for acoustic event recognition

  2021cites this paper
• A Comparative Survey of Feature Extraction and Machine Learning Methods in Diverse Acoustic Environments

  2021cites this paper
• Environmental Sound Classification on the Edge: Deep Acoustic Networks for Extremely Resource-Constrained Devices

  2021cites this paper
• Tiny Transformers for Environmental Sound Classification at the Edge

  2021cites this paper
• Visualization and categorization of ecological acoustic events based on discriminant features

  2021cites this paper
• Convolutional Neural Network-Gated Recurrent Unit Neural Network with Feature Fusion for Environmental Sound Classification

  2021influential citation
• Sound detection for study room monitoring and evaluation

  2021cites this paper
• Environmental sound classification using convolution neural networks with different integrated loss functions

  2021cites this paper
• Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained Devices

  2021cites this paper
• RETRACTED: Urban Sound Classification Using Convolutional Neural Network Model

  2021cites this paper
• Generative Model Driven Representation Learning in a Hybrid Framework for Environmental Audio Scene and Sound Event Recognition

  2020cites this paper
• Cyber-Physical Analytics: Environmental Sound Classification at the Edge

  2020cites this paper
• Urban Sound Classification Using Convolutional Neural Network and Long Short Term Memory Based on Multiple Features

  2020influential citation
• Closed-Form Pre-Training for Small-Sample Environmental Sound Recognition

  2020cites this paper
• An Ensemble of Convolutional Neural Networks for Audio Classification

  2020cites this paper
• Environment Sound Classification System Based on Hybrid Feature and Convolutional Neural Network

  2020cites this paper
• Impact of Minimum Hyperspherical Energy Regularization on Time-Frequency Domain Networks for Singing Voice Separation

  2020cites this paper
• The use of non-linear acoustic analysis to objectively evaluate the voice of people with Parkinson's disease

  2020cites this paper
• ESResNet: Environmental Sound Classification Based on Visual Domain Models

  2020cites this paper
• Urban sound classification based on 2-order dense convolutional network using dual features

  2020cites this paper
• Multi-stream Network With Temporal Attention For Environmental Sound Classification

  2019cites this paper
• Environmental Sound Classification with Parallel Temporal-Spectral Attention

  2019cites this paper
• Environment Sound Classification Using Multiple Feature Channels and Attention Based Deep Convolutional Neural Network

  2019cites this paper
• Learning discriminative and robust time-frequency representations for environmental sound classification

  2019cites this paper
• Environment Sound Classification using Multiple Feature Channels and Deep Convolutional Neural Networks

  2019cites this paper
• Environmental Audio Scene and Sound Event Recognition for Autonomous Surveillance

  2019cites this paper
• Meta-Analysis of Acoustic Feature Extraction for Machine Listening Systems

  2019cites this paper
• Environmental acoustic transformation and feature extraction for machine hearing

  2019cites this paper
• Deep Convolutional Neural Network with Mixup for Environmental Sound Classification

  2018influential citation
• Learning Environmental Sounds with Multi-scale Convolutional Neural Network

  2018cites this paper
• Convolutional Recurrent Neural Networks for Urban Sound Classification Using Raw Waveforms

  2018cites this paper
• Unsupervised Filterbank Learning Using Convolutional Restricted Boltzmann Machine for Environmental Sound Classification

  2017cites this paper