Prediction of Psychoacoustic Metrics Using Combination of Wavelet Packet Transform and an Optimized Artificial Neural Network
In this paper, a modified sound quality evaluation (SQE) model is developed based on combination of an optimized artificial neural network (ANN) and the wavelet packet transform (WPT). The presented SQE model is a signal processing technique, which can be implemented in current microphones for predi...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Institute of Fundamental Technological Research Polish Academy of Sciences
2019-07-01
|
| Series: | Archives of Acoustics |
| Subjects: | |
| Online Access: | https://acoustics.ippt.pan.pl/index.php/aa/article/view/2460 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839604256896712704 |
|---|---|
| author | Mehdi POURSEIEDREZAEI Ali LOGHMANI Mehdi KESHMIRI |
| author_facet | Mehdi POURSEIEDREZAEI Ali LOGHMANI Mehdi KESHMIRI |
| author_sort | Mehdi POURSEIEDREZAEI |
| collection | DOAJ |
| description | In this paper, a modified sound quality evaluation (SQE) model is developed based on combination of an optimized artificial neural network (ANN) and the wavelet packet transform (WPT). The presented SQE model is a signal processing technique, which can be implemented in current microphones for predicting the sound quality. The proposed method extracts objective psychoacoustic metrics including loudness, sharpness, roughness, and tonality from sound samples, by using a special selection of multi-level nodes of the WPT combined with a trained ANN. The model is optimized using the particle swarm optimization (PSO) and the back propagation (BP) algorithms. The obtained results reveal that the proposed model shows the lowest mean square error and the highest correlation with human perception while it has the lowest computational cost compared to those of the other models and software. |
| format | Article |
| id | doaj-art-2a84d6b806d64fb9a699ca0908e08ae9 |
| institution | Matheson Library |
| issn | 0137-5075 2300-262X |
| language | English |
| publishDate | 2019-07-01 |
| publisher | Institute of Fundamental Technological Research Polish Academy of Sciences |
| record_format | Article |
| series | Archives of Acoustics |
| spelling | doaj-art-2a84d6b806d64fb9a699ca0908e08ae92025-08-02T04:03:32ZengInstitute of Fundamental Technological Research Polish Academy of SciencesArchives of Acoustics0137-50752300-262X2019-07-0144310.24425/aoa.2019.129271Prediction of Psychoacoustic Metrics Using Combination of Wavelet Packet Transform and an Optimized Artificial Neural NetworkMehdi POURSEIEDREZAEI0Ali LOGHMANI1Mehdi KESHMIRI2Isfahan University of TechnologyIsfahan University of TechnologyIsfahan University of TechnologyIn this paper, a modified sound quality evaluation (SQE) model is developed based on combination of an optimized artificial neural network (ANN) and the wavelet packet transform (WPT). The presented SQE model is a signal processing technique, which can be implemented in current microphones for predicting the sound quality. The proposed method extracts objective psychoacoustic metrics including loudness, sharpness, roughness, and tonality from sound samples, by using a special selection of multi-level nodes of the WPT combined with a trained ANN. The model is optimized using the particle swarm optimization (PSO) and the back propagation (BP) algorithms. The obtained results reveal that the proposed model shows the lowest mean square error and the highest correlation with human perception while it has the lowest computational cost compared to those of the other models and software.https://acoustics.ippt.pan.pl/index.php/aa/article/view/2460sound quality measurementpsychoacoustic metricswavelet packet transformoptimized artificial neural network |
| spellingShingle | Mehdi POURSEIEDREZAEI Ali LOGHMANI Mehdi KESHMIRI Prediction of Psychoacoustic Metrics Using Combination of Wavelet Packet Transform and an Optimized Artificial Neural Network Archives of Acoustics sound quality measurement psychoacoustic metrics wavelet packet transform optimized artificial neural network |
| title | Prediction of Psychoacoustic Metrics Using Combination of Wavelet Packet Transform and an Optimized Artificial Neural Network |
| title_full | Prediction of Psychoacoustic Metrics Using Combination of Wavelet Packet Transform and an Optimized Artificial Neural Network |
| title_fullStr | Prediction of Psychoacoustic Metrics Using Combination of Wavelet Packet Transform and an Optimized Artificial Neural Network |
| title_full_unstemmed | Prediction of Psychoacoustic Metrics Using Combination of Wavelet Packet Transform and an Optimized Artificial Neural Network |
| title_short | Prediction of Psychoacoustic Metrics Using Combination of Wavelet Packet Transform and an Optimized Artificial Neural Network |
| title_sort | prediction of psychoacoustic metrics using combination of wavelet packet transform and an optimized artificial neural network |
| topic | sound quality measurement psychoacoustic metrics wavelet packet transform optimized artificial neural network |
| url | https://acoustics.ippt.pan.pl/index.php/aa/article/view/2460 |
| work_keys_str_mv | AT mehdipourseiedrezaei predictionofpsychoacousticmetricsusingcombinationofwaveletpackettransformandanoptimizedartificialneuralnetwork AT aliloghmani predictionofpsychoacousticmetricsusingcombinationofwaveletpackettransformandanoptimizedartificialneuralnetwork AT mehdikeshmiri predictionofpsychoacousticmetricsusingcombinationofwaveletpackettransformandanoptimizedartificialneuralnetwork |