Enhanced blind source separation algorithm for highly correlated mixtures
S Wang, D Ramakrishnan, S Gupta… - US Patent 8,223,988, 2012 - Google Patents
An enhanced blind source separation technique is provided to improve separation of highly
correlated signal mixtures. A beamforming algorithm is used to precondition correlated first …
correlated signal mixtures. A beamforming algorithm is used to precondition correlated first …
Apparatus and method of noise and echo reduction in multiple microphone audio systems
S Wang, SK Gupta, ELT Choy - US Patent 8,175,871, 2012 - Google Patents
GOL 9/00(2006.01) iety of noise Suppressi hniq dapp GOL 7/00(2006.01) that can be
selectively applied to signals received using mul H04B I5/00(2006.01) tiple microphones …
selectively applied to signals received using mul H04B I5/00(2006.01) tiple microphones …
Tabby Talks: An automated tool for the assessment of childhood apraxia of speech
Children with developmental disabilities such as childhood apraxia of speech (CAS) require
repeated intervention sessions with a speech therapist, sometimes extending over several …
repeated intervention sessions with a speech therapist, sometimes extending over several …
Multiple microphone voice activity detector
S Wang, SK Gupta, ELT Choy - US Patent 8,954,324, 2015 - Google Patents
Voice activity detection using multiple microphones can be based on a relationship between
an energy at each of a speech reference microphone and a noise reference microphone …
an energy at each of a speech reference microphone and a noise reference microphone …
Robust voice activity detection directed by noise classification
In this paper voice activity detection (VAD) is formulated as a two-class classification
problem using support vector machines (SVM). The proposed method combines a noise …
problem using support vector machines (SVM). The proposed method combines a noise …
Voice activity detection based on using wavelet packet
M Eshaghi, MRK Mollaei - Digital Signal Processing, 2010 - Elsevier
This paper, presents a robust voice activity detection (VAD) technique based on wavelet
packet. In this technique sub-bands and their amplitudes are represented as the vectors for …
packet. In this technique sub-bands and their amplitudes are represented as the vectors for …
Extraction of threshold voltage degradation modeling due to negative bias temperature instability in circuits with I/O measurements
Negative Bias Temperature Instability (NBTI) is a serious reliability issue for pMOS
transistors. Normally, degradation due to NBTI is modeled based on test structure data or …
transistors. Normally, degradation due to NBTI is modeled based on test structure data or …
An improved speech endpoint detection based on adaptive sub-band selection spectral variance
C Zhang, M Dong - 2016 35th Chinese Control Conference …, 2016 - ieeexplore.ieee.org
Speech endpoint detection is an important component in different speech processing
systems. The endpoint detection using basic spectral variance becomes difficult and …
systems. The endpoint detection using basic spectral variance becomes difficult and …
[PDF][PDF] A Framework for Automated Marmoset Vocalization Detection and Classification.
This paper describes a novel framework for automated marmoset vocalization detection and
classification from within long audio streams recorded in a noisy animal room, where …
classification from within long audio streams recorded in a noisy animal room, where …
[PDF][PDF] A model based voice activity detector for noisy environments.
This paper presents a model-based voice activity detector (VAD) aimed at operating in low
signal to noise ratio conditions and non-stationary noise environments. The proposed …
signal to noise ratio conditions and non-stationary noise environments. The proposed …