Proceedings ArticleDOI
Speech perception based algorithm for the separation of overlapping speech signal
Michael Christopher Orr,Duc-Son Pham,Brian J Lithgow,Robert Mahony +3 more
- pp 341-344
Reads0
Chats0
TLDR
Preliminary results show that some phonetic information, such as articulation placement and identification of voiced/unvoiced sections, can be extracted from the kurtosis analysis.Abstract:
An algorithm for the analysis of speech utilising the time frequency properties of wavelets is introduced. The extracted wavelet coefficients are analysed using two techniques, firstly a covariance matrix is generated to provide information about speaker characteristics. Second, the kurtosis of the wavelet coefficients is used to facilitate the detection of multiple speakers. Preliminary results show that some phonetic information, such as articulation placement and identification of voiced/unvoiced sections, can be extracted from the kurtosis analysis.read more
Citations
More filters
Journal ArticleDOI
Comparison of techniques for environmental sound recognition
Michael A. Cowling,Renate Sitte +1 more
TL;DR: A comprehensive comparative study of artificial neural networks, learning vector quantization and dynamic time warping classification techniques combined with stationary/non-stationary feature extraction for environmental sound recognition shows 70% recognition using mel frequency cepstral coefficients or continuous wavelet transform with dynamic time Warping.
Journal ArticleDOI
Using One-Class SVMs and Wavelets for Audio Surveillance
TL;DR: 1-SVM-based multiclass classification approach overperforms the conventional hidden Markov model-based system in the experiments conducted, the improvement in the error rate can reach 50%.
Posted Content
Comparison of Time-Frequency Representations for Environmental Sound Classification using Convolutional Neural Networks.
TL;DR: This study supports the hypothesis that time-frequency representations are valuable in learning useful features for sound classification and observes that the optimal window size during transformation is dependent on the characteristics of the audio signal and architecturally, 2D convolution yielded better results in most cases compared to 1D.
Dissertation
Non-Speech Environmental Sound Classification System for Autonomous Surveillance
TL;DR: This thesis investigates techniques to recognise environmental non-speech sounds and their direction, with the purpose of using these techniques in an autonomous mobile surveillance robot, and presents advanced methods to improve the accuracy and efficiency of these techniques.
Journal ArticleDOI
Audio sounds classification using scattering features and support vectors machines for medical surveillance
Sameh Souli,Zied Lachiri +1 more
TL;DR: The method integrates ability of PCA to de-correlate the coefficients by extracting a linear relationship with what of scatter transform analysis to derive feature vectors used for environmental sounds classification, and shows the superiority of this novel sound recognition method.
References
More filters
Journal ArticleDOI
Robust identification of a nonminimum phase system: Blind adjustment of a linear equalizer in data communications
TL;DR: In this paper, an unknown linear time-invariant system without control, driven by a white noise with known distribution, is considered, and the identification of both gain and phase of the system, observing only the output, is presented.
Journal ArticleDOI
Description and generation of spherically invariant speech-model signals
H. Brehm,W. Stammler +1 more
TL;DR: In this paper, spherically invariant random processes (SIRPs) are used as stationary models for speech signals in telephone channels and a comprehensive mathematical treatment is achieved by means of Meijer's G -functions.
Proceedings ArticleDOI
The Australian National Database of Spoken Language
TL;DR: The novel collaborative structure and procedures for selecting speakers, the material recorded, the recording environment, and subsequent annotation and descriptive procedures are described.
Proceedings ArticleDOI
Speech separation by kurtosis maximization
J.P. LeBlanc,P.L. De Leon +1 more
TL;DR: A computationally efficient method of separating mixed speech signals using a recursive adaptive gradient descent technique with the cost function designed to maximize the kurtosis of the output (separated) signals is presented.
Journal ArticleDOI
Algorithms for separating the speech of interfering talkers: Evaluations with voiced sentences, and normal‐hearing and hearing‐impaired listeners
TL;DR: Two signal-processing algorithms, derived from those described by Stubbs and Summerfield, were used to separate the voiced speech of two talkers speaking simultaneously, at similar intensities, in a single channel and gave significant increases in intelligibility to both groups of listeners.