Better speech recognition accuracy in noisy environments using voice extraction

Author(s):  
W. Zuluaga ◽  
K. Amalashekaran ◽  
J. Chisholm
2012 ◽  
Vol 229-231 ◽  
pp. 1296-1299 ◽  
Author(s):  
Yan Li Liu ◽  
De Xiang Zhang ◽  
Ming Wei Ji

Accurate endpoint detection is crucial for speech recognition accuracy. A novel approach that finds robust features for endpoint detection based on the empirical mode decomposition (EMD) algorithm and spectral entropy in a noisy environment is proposed. With the EMD, the noise signals can be decomposed into different numbers of sub-signals called intrinsic mode functions (IMFs), which is a zero-mean AM-FM component. Then spectral entropy can be used to extract the desired feature for IMF components. In order to show the effectiveness of the proposed method, we present examples showing that the new measure is more effective than traditional measures. The experiments show that the proposed algorithm can suppress different noise types with different SNR, and the algorithm is robust in the real signal tests.


2004 ◽  
Author(s):  
Martin Graciarena ◽  
Federico Cesari ◽  
Horacio Franco ◽  
Greg Myers ◽  
Cregg Cowan ◽  
...  

2018 ◽  
Vol 39 (04) ◽  
pp. 349-363 ◽  
Author(s):  
Eric Hoover ◽  
Pamela Souza

AbstractSubstantial loss of cochlear function is required to elevate pure-tone thresholds to the severe hearing loss range; yet, individuals with severe or profound hearing loss continue to rely on hearing for communication. Despite the impairment, sufficient information is encoded at the periphery to make acoustic hearing a viable option. However, the probability of significant cochlear and/or neural damage associated with the loss has consequences for sound perception and speech recognition. These consequences include degraded frequency selectivity, which can be assessed with tests including psychoacoustic tuning curves and broadband rippled stimuli. Because speech recognition depends on the ability to resolve frequency detail, a listener with severe hearing loss is likely to have impaired communication in both quiet and noisy environments. However, the extent of the impairment varies widely among individuals. A better understanding of the fundamental abilities of listeners with severe and profound hearing loss and the consequences of those abilities for communication can support directed treatment options in this population.


2016 ◽  
Vol 22 (2) ◽  
pp. 100-105
Author(s):  
Behnam Asefisaray ◽  
Erhan Mengüşoğlu ◽  
Murat Hacıömeroğlu ◽  
Hayri Sever

Sign in / Sign up

Export Citation Format

Share Document