Robust feature extraction for speech recognition by enhancing auditory spectrum

2012 ◽  
Author(s):  
Md Jahangir Alam ◽  
Patrick Kenny ◽  
Douglas O'Shaughnessy
Keyword(s):  
Feature Extraction ◽  
Speech Recognition ◽  
Robust Feature Extraction

Multi-microphone speech recognition integrating beamforming, robust feature extraction, and advanced DNN/RNN backend

2017 ◽  
Vol 46 ◽  
pp. 401-418 ◽  
Author(s):  
Takaaki Hori ◽  
Zhuo Chen ◽  
Hakan Erdogan ◽  
John R. Hershey ◽  
Jonathan Le Roux ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Speech Recognition ◽  
Robust Feature Extraction

scholarly journals A Robust Feature Extraction Method for Real-Time Speech Recognition System on a Raspberry Pi 3 Board

2019 ◽  
Vol 9 (2) ◽  
pp. 4066-4070 ◽  
Author(s):  
A. Mnassri ◽  
M. Bennasr ◽  
C. Adnane
Keyword(s):  
Feature Extraction ◽  
Speech Recognition ◽  
Real Time ◽  
Extraction Method ◽  
Recognition System ◽  
Raspberry Pi ◽  
Discrete Wavelet ◽  
Speech Recognition System ◽  
Feature Extraction Method ◽  
Robust Feature Extraction

The development of a real-time automatic speech recognition system (ASR) better adapted to environmental variabilities, such as noisy surroundings, speaker variations and accents has become a high priority. Robustness is required, and it can be performed at the feature extraction stage which avoids the need for other pre-processing steps. In this paper, a new robust feature extraction method for real-time ASR system is presented. A combination of Mel-frequency cepstral coefficients (MFCC) and discrete wavelet transform (DWT) is proposed. This hybrid system can conserve more extracted speech features which tend to be invariant to noise. The main idea is to extract MFCC features by denoising the obtained coefficients in the wavelet domain by using a median filter (MF). The proposed system has been implemented on Raspberry Pi 3 which is a suitable platform for real-time requirements. The experiments showed a high recognition rate (100%) in clean environment and satisfying results (ranging from 80% to 100%) in noisy environments at different signal to noise ratios (SNRs).

Sign in / Sign up

Export Citation Format

Share Document