Audio classification from time-frequency texture

@article{Yu2009AudioCF,
  title={Audio classification from time-frequency texture},
  author={Guoshen Yu and Jean-Jacques E. Slotine},
  journal={2009 IEEE International Conference on Acoustics, Speech and Signal Processing},
  year={2009},
  pages={1677-1680}
}
  • Guoshen Yu, J. Slotine
  • Published 2009
  • Computer Science
  • 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
Time-frequency representations of audio signals often resemble texture images. This paper derives a simple audio classification algorithm based on treating sound spectrograms as texture images. The algorithm is inspired by an earlier visual classification scheme particularly efficient at classifying textures. While solely based on time-frequency texture features, the algorithm achieves surprisingly good performance in musical instrument classification experiments. 
Histogram of Gradients of Time–Frequency Representations for Audio Scene Classification
TLDR
The approach for classifying acoustic scenes is based on transforming the audio signal into a time-frequency representation and then in extracting relevant features about shapes and evolutions of time- frequency structures based on histogram of gradients that are subsequently fed to a multi-class linear support vector machines. Expand
Audio classification using dominant spatial patterns in time-frequency space
TLDR
This paper presents a novel audio discrimination algorithm using spatial features in time-frequency (TF) space that is more noise robust and performs better than the recently reported methods. Expand
An audio feature extraction scheme based on spectral decomposition
TLDR
An audio feature extraction scheme based on spectral decomposition where the decomposition is performed iteratively by matching-pursuit in frequency domain where the proposed feature outperforms other spectral and cepstral features. Expand
Local Tetra Pattern Texture Features for Environmental Sound Event Classification
  • Khine Zar Thwe, Nu War
  • Computer Science
  • 2017 18th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT)
  • 2017
TLDR
This paper presents sound classification by combining of image processing and signal processing to classify the data accurately. Expand
Speech and music classification using hybrid Form of spectrogram and fourier transformation
TLDR
This paper presents the technique for feature extraction to classify speech and music audio data and shows that the acceptable classification accuracy of the proposed technique is achieved. Expand
Environmental Sounds Classification Based on Visual Features
TLDR
A new approach that extracts visual features from sound spectrograms as texture images, and extracts the time-frequency structures by using a translation-invariant wavelet transform and a patch transform alternated with local maximum and global maximum to pursuit scale and translation invariance. Expand
Spectrogram based features selection using multiple kernel learning for speech/music discrimination
TLDR
The experimental results show that the proposed MKL based algorithm applied for SMD of a standard dataset yields noticeable improvements in classification accuracy and tolerance toward different noise types compared to the existing methods. Expand
Environmental sound classification based on time-frequency representation
  • Khine Zar Thwe, Nu War
  • Computer Science
  • 2017 18th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)
  • 2017
TLDR
A feature extraction method for environmental sound event classification based on time-frequency representation such as spectrogram, which is used to extract features with local binary pattern of three different radius and neighborhood sizes. Expand
Analysis of spectrogram image methods for sound event classification
TLDR
The idea and structure behind six recent spectrogram image methods are introduced and their performance on a large database containing 50 different environmental sounds is analysed to give a standardised comparison that is not often available in sound event classification tasks. Expand
Sound-Event Classification Using Robust Texture Features for Robot Hearing
TLDR
This work proposes to extract the local binary pattern (LBP) from the logarithm of the Gammatone-like spectrogram, and proposes two projection-based LBP features to better capture the texture information of the spectrogram. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 31 REFERENCES
Audio Denoising by Time-Frequency Block Thresholding
TLDR
A block thresholding estimation procedure is introduced, which adjusts all parameters adaptively to signal property by minimizing a Stein estimation of the risk. Expand
CLASSIFICATION OF MUSIC SIGNALS IN THE VISUAL DOMAIN
With the huge increase in the availability of digital music, it has become more important to automate the task of querying a database of musical pieces. At the same time, a computational solution ofExpand
Content-Based Classification, Search, and Retrieval of Audio
TLDR
The audio analysis, search, and classification engine described here reduces sounds to perceptual and acoustical features, which lets users search or retrieve sounds by any one feature or a combination of them, by specifying previously learned classes based on these features. Expand
Content-Based Audio Classification and Retrieval Using SVM Learning
TLDR
Given a feature set, which in this work is composed of perceptual and cepstral feature, optimal class boundaries between classes are learned from training data by using SVMs. Expand
Musical instrument recognition by pairwise classification strategies
TLDR
It is shown that higher recognition rates can be reached with pairwise optimized subsets of features in association with SVM classification using a radial basis function kernel. Expand
Content-Based Classification, Search, and Retrieval of Audio
Many audio and multimedia applications would benefit from the ability to classify and search for audio based on characteristics of the audio rather than by keywords. These include multimedia databa...
A wavelet tour of signal processing
Introduction to a Transient World. Fourier Kingdom. Discrete Revolution. Time Meets Frequency. Frames. Wavelet Zoom. Wavelet Bases. Wavelet Packet and Local Cosine Bases. An Approximation Tour.Expand
Content-based audio classification and retrieval by support vector machines
  • G. Guo, S. Li
  • Computer Science, Medicine
  • IEEE Trans. Neural Networks
  • 2003
TLDR
The SVMs with a binary tree recognition strategy are used to tackle the audio classification problem and experimental comparisons for audio retrieval are presented to show the superiority of this novel metric, called distance-from-boundary (DFB). Expand
Spectral completion of partially masked sounds
TLDR
The auditory system partially corrects for the effects of masking in natural environments, by using the audible, unmasked portions of an object's spectrum to fill in the inaudible portions of a sound's spectrum. Expand
FastWavelet-Based Visual Classification
TLDR
This work investigates a biologically motivated approach to fast visual classification using standard wavelet transforms and patch transforms to parallel the tuning of visual cortex V1 and V4 cells, alternated with max operations to achieve scale and translation invariance and introduces a simple attention-like feedback mechanism. Expand
...
1
2
3
4
...