Md Jamal, Norezmi (2022) Speech enhancement using deep neural network based on mask estimation and harmonic regeneration noise reduction for single channel microphone. Doctoral thesis, Universiti Tun Hussein Onn Malaysia.
|
Text
24p NOREZMI MD JAMAL.pdf Download (1MB) | Preview |
|
![[img]](http://eprints.uthm.edu.my/style/images/fileicons/text.png) |
Text (Copyright Declaration)
NOREZMI MD JAMAL COPYRIGHT DECLARATION.pdf Restricted to Repository staff only Download (131kB) | Request a copy |
|
|
Text (Full Text)
NOREZMI MD JAMAL WATERMARK.pdf Restricted to Registered users only Download (5MB) | Request a copy |
Abstract
The development of speech-enabled mobile applications has greatly improved human-computer interaction in recent years. These applications are flexible and convenient for users. Since the speech signal is captured in mobile conditions, it may easily be contaminated by background noises, which may result in a complicated computation and require speech enhancement algorithm. Thus, the performance of speech applications can be degraded when signal-to-noise ratio (SNR) is low and nonstationary noise is present. Moreover, the task of removing noises without causing speech distortion is also challenging, in which the quality and intelligibility of speech are affected. In order to overcome these issues, a supervised Deep Neural Network (DNN) algorithm predicted constrained Wiener Filter (cWF) target mask algorithm based on extracted Gammatone filter bank power spectrum (GF-TF) features and trained model is developed. As a result, the trained model with GF-TF features and cross-speech dataset produced promising results, while the proposed target mask scored higher on the perceptual evaluation of speech quality (PESQ) and short-time objective intelligibility (STOI) tests. On top of that, a modified Harmonic Regeneration Noise Reduction (HRNR) algorithm is proposed as a post-filtering strategy to enhance speech signal due to residual noise being introduced after DNN prediction. Results from TIMIT dataset revealed that average STOI scores for the joint algorithm are higher than those of DNN, conventional HRNR and Log Minimum Mean Square Error (Log-MMSE) algorithms. With SNR of -5 dB, an improvement of 4% over DNN algorithm, 36% over conventional HRNR algorithm, and 12% over Log-MMSE algorithm are obtained. While the average PESQ score is less affected after post-filtering strategy. Thus, this work has contributed to improve speech intelligibility from noisy backgrounds at low SNR as it can be deployed in speechenabled mobile applications.
| Item Type: | Thesis (Doctoral) |
|---|---|
| Subjects: | T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5101-6720 Telecommunication. Including telegraphy, telephone, radio, radar, television |
| Divisions: | Faculty of Electrical and Electronic Engineering > Department of Electrical Engineering |
| Depositing User: | Mrs. Sabarina Che Mat |
| Date Deposited: | 27 Feb 2023 01:01 |
| Last Modified: | 27 Feb 2023 01:01 |
| URI: | http://eprints.uthm.edu.my/id/eprint/8464 |
Actions (login required)
 |
View Item |