Optimized joint noise suppression and dereverberation based on blind signal extraction for hands-free speech recognition system

2014 ◽  
Author(s):  
Fine D. Aprilyanti ◽  
Hiroshi Saruwatari ◽  
Satoshi Nakamura ◽  
Tomoya Takatani
Keyword(s):  
Speech Recognition ◽  
Free Speech ◽  
Noise Suppression ◽  
Recognition System ◽  
Signal Extraction ◽  
Speech Recognition System ◽  
Blind Signal ◽  
Blind Signal Extraction

scholarly journals Direct Recovery of Clean Speech Using a Hybrid Noise Suppression Algorithm for Robust Speech Recognition System

2012 ◽  
Vol 2012 ◽  
pp. 1-9
Author(s):  
Peng Dai ◽  
Ing Yann Soon ◽  
Rui Tao
Keyword(s):  
Speech Recognition ◽  
Noise Suppression ◽  
Recognition Rate ◽  
Nonlinear Function ◽  
Recognition System ◽  
Speech Recognition System ◽  
Direct Solution ◽  
Power Domain ◽  
Discontinuity Problem ◽  
Mel Frequency Cepstral Coefficient

A new log-power domain feature enhancement algorithm named NLPS is developed. It consists of two parts, direct solution of nonlinear system model and log-power subtraction. In contrast to other methods, the proposed algorithm does not need prior speech/noise statistical model. Instead, it works by direct solution of the nonlinear function derived from the speech recognition system. Separate steps are utilized to refine the accuracy of estimated cepstrum by log-power subtraction, which is the second part of the proposed algorithm. The proposed algorithm manages to solve the speech probability distribution function (PDF) discontinuity problem caused by traditional spectral subtraction series algorithms. The effectiveness of the proposed filter is extensively compared using the standard database, AURORA2. The results show that significant improvement can be achieved by incorporating the proposed algorithm. The proposed algorithm reaches a recognition rate of over 86% for noisy speech (average from SNR 0 dB to 20 dB), which means a 48% error reduction over the baseline Mel-frequency Cepstral Coefficient (MFCC) system.

Design Of A Voice Controlled Home Automation System Using Deep Learning Convolutional Neural Network (DL-CNN)

2020 ◽  
Vol 8 (1) ◽  
pp. 57-73
Author(s):  
Lery Sakti Ramba
Keyword(s):  
Deep Learning ◽  
Speech Recognition ◽  
Background Noise ◽  
Electronic Devices ◽  
Recognition System ◽  
Background Intensity ◽  
Automation System ◽  
Home Automation ◽  
Speech Recognition System ◽  
Home Automation System

The purpose of this research is to design home automation system that can be controlled using voice commands. This research was conducted by studying other research related to the topics in this research, discussing with competent parties, designing systems, testing systems, and conducting analyzes based on tests that have been done. In this research voice recognition system was designed using Deep Learning Convolutional Neural Networks (DL-CNN). The CNN model that has been designed will then be trained to recognize several kinds of voice commands. The result of this research is a speech recognition system that can be used to control several electronic devices connected to the system. The speech recognition system in this research has a 100% success rate in room conditions with background intensity of 24dB (silent), 67.67% in room conditions with 42dB background noise intensity, and only 51.67% in room conditions with background intensity noise 52dB (noisy). The percentage of the success of the speech recognition system in this research is strongly influenced by the intensity of background noise in a room. Therefore, to obtain optimal results, the speech recognition system in this research is more suitable for use in rooms with low intensity background noise.

Sign in / Sign up

Export Citation Format

Share Document