Two-Microphone Dereverberation for Automatic Speech Recognition of Polish

Kundegorski, Mikolaj E.; Jackson, Philip J. B.; Ziółko, Bartosz

doi:10.2478/aoa-2014-0045

Cited by 7 publications

(5 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, many classification methods were developed in the literature [32][33][34][35][36][37][38][39][40][41][42][43][44][45]. The artificial intelligence in diagnostics of electric machines was discussed [15], [25].…”

Section: Bayes Classifiermentioning

confidence: 99%

Recognition of Thermal Images of Direct Current Motor with Application of Area Perimeter Vector and Bayes Classifier

Głowacz¹,

Głowacz²,

Głowacz³

2015

Measurement Science Review

View full text Add to dashboard Cite

Infrared thermography can measure the temperature of a surface remotely. In this article authors present a diagnostic method of incipient fault detection. The proposed approach is based on pattern recognition. It uses monochrome thermal images of the rotor with the application of an area perimeter vector and a Bayes classifier. The investigations have been carried out for direct current motor without faults and motor with shorted rotor coils. The measurements were performed in the laboratory. The efficiency of recognition using the area perimeter vector and the Bayes classifier was 100 %. The investigations show that the method based on recognition of thermal images can be profitable for engineers. The proposed method can be applied in mining, metallurgy, fuel industry and in factories where electrical motors are used.

show abstract

Section: Bayes Classifiermentioning

confidence: 99%

Recognition of Thermal Images of Direct Current Motor with Application of Area Perimeter Vector and Bayes Classifier

Głowacz¹,

Głowacz²,

Głowacz³

2015

Measurement Science Review

View full text Add to dashboard Cite

show abstract

“…Engineers and scientists developed a great variety of feature extraction and classification methods [32][33][34][35][36][37][38][39][40][41][42][43][44][45][46][47]. Classification methods are often based on artificial intelligence.…”

Section: G Neural Network With Backpropagation Algorithmmentioning

confidence: 99%

Recognition of Acoustic Signals of Synchronous Motors with the Use of MoFS and Selected Classifiers

Głowacz

2015

Measurement Science Review

View full text Add to dashboard Cite

This paper proposes an approach based on acoustic signals for detecting faults appearing in synchronous motors. Acoustic signals of a machine were used for fault detection. These faults contained: broken coils and shorted stator coils. Acoustic signals were used to assess the usefulness of early fault diagnostic of synchronous motors. The acoustic signal recognition system was based on methods of data processing: normalization of the amplitude, Fast Fourier Transform (FFT), method of frequency selection (MoFS), backpropagation neural network, classifier based on words coding, and Nearest Neighbor classifier. A plan of study of acoustic signals of synchronous motors was proposed. Software of acoustic signal recognition of synchronous motors was implemented. Four states of a synchronous motor were used in analysis. A pattern creation process was carried out for 28 training samples of noise. An identification process was carried out for 60 test samples. This system can be used to diagnose synchronous motors and other electrical machines.

show abstract

“…The problem of classification was already discussed in literature [29][30][31][32][33][34][35][36][37][38][39][40][41][42][43][44][45]. Neural networks were described in many scientific articles [37][38][39][40][41][42].…”

Section: Nearest Neighbour Classifiermentioning

confidence: 99%

Fault diagnostics of DC motor using acoustic signals and MSAF-RATIO30-EXPANDED

Głowacz

2016

Archives of Electrical Engineering

View full text Add to dashboard Cite

An early fault diagnostic method of Direct Current motors was presented in this article. The proposed method used acoustic signals of a motor. A method of feature extraction called MSAF-RATIO30-EXPANDED (method of selection of amplitudes of frequencies -ratio 30% of maximum of amplitude -expanded) was presented and implemented. An analysis of proposed method was carried out for early fault states of a real DC motor. Four following states of the DC motor were measured and analyzed: the healthy DC motor, DC motor with 3 shorted rotor coils, DC motor with 6 shorted rotor coils, DC motor with a broken coil. Measured states were caused by natural degradation of the DC motor. The obtained results of analysis were good. The presented early fault diagnostic method can be used for protection of DC motors.

show abstract

Two-Microphone Dereverberation for Automatic Speech Recognition of Polish

Cited by 7 publications

References 29 publications

Recognition of Thermal Images of Direct Current Motor with Application of Area Perimeter Vector and Bayes Classifier

Recognition of Thermal Images of Direct Current Motor with Application of Area Perimeter Vector and Bayes Classifier

Recognition of Acoustic Signals of Synchronous Motors with the Use of MoFS and Selected Classifiers

Fault diagnostics of DC motor using acoustic signals and MSAF-RATIO30-EXPANDED

Contact Info

Product

Resources

About