Teager energy based feature parameters for speech recognition in car noise

Jabloun, F.; Çetin, A. Enis; Erzin, Engin

doi:10.1109/97.789604

Cited by 96 publications

(43 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Different methods are used to analyze the audio signal in order to extract the features and use them in the fall detection approach. Such methods are analysis of the audio signal based on wavelet domain feature extraction or analysis based on Fourier domain feature extraction [11]. The problem with this type of detectors is that other sounds coming from the background may be mixed with falling events; so again, the reliability of the system is in question.…”

Section: Related Approachesmentioning

confidence: 99%

Real Time Recognition of Elderly Daily Activity using Fuzzy Logic through Fusion of Motion and Location Data

Khawandi¹,

Daya²,

Chauvet³

2012

IJCA

View full text Add to dashboard Cite

One of the major problems that may encounter old people at home is falling. Approximately, one of three adults of the age of 65 or older falls every year. The World Health Organization reports that injuries due to falls are the third most common cause of chronic disability. In this paper, we proposed an approach to indoor human daily activity recognition, which combines motion and location data by using a webcam system, with a particular interest to the problem of fall detection. The proposed system identifies the face and the body in a given area, collects motion data such as face and body speeds and location data such as center of mass and aspect ratio; then the extracted parameters will be fed to a Fuzy logic classifier that classify the fall event in two classes: fall and not fall.

show abstract

Section: Related Approachesmentioning

confidence: 99%

Real Time Recognition of Elderly Daily Activity using Fuzzy Logic through Fusion of Motion and Location Data

Khawandi¹,

Daya²,

Chauvet³

2012

IJCA

View full text Add to dashboard Cite

show abstract

“…In practice, since corrupted noise is effectively suppressed by the TE operator, the TE operator can provide better ability to discriminate speech characteristics from noise. The TE operator is easily implemented through the time domain and is defined as given by [5], [6]:…”

Section: Review Of the Teager Energy Operatormentioning

confidence: 99%

“…In this letter, we propose a novel approach to the VAD algorithm in which global speech absence probability (GSAP) [3], based on Teager energy (TE) [5], [6], is derived to improve the performance of VAD in various noisy environments. Statistical model-based GSAP is one of the feature parameters which is widely adopted in the decision rule for VAD, and it is used as the smoothing parameter for updating the noise signal in the speech enhancement algorithm.…”

Section: Introductionmentioning

confidence: 99%

Voice Activity Detection Using Global Speech Absence Probability Based on Teager Energy for Speech Enhancement

Park

Lee

2012

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYIn this paper, we propose a novel voice activity detection (VAD) algorithm using global speech absence probability (GSAP) based on Teager energy (TE) for speech enhancement. The proposed method provides a better representation of GSAP, resulting in improved decision performance for speech and noise segments by the use of a TE operator which is employed to suppress the influence of noise signals. The performance of our approach is evaluated by objective tests under various environments, and it is found that the suggested method yields better results than conventional schemes. key words: voice activity detection, speech absence probability, teager energy

show abstract

“…Wavelet filterbanks have been proposed for speech recognition (Jabloun et al, 1999) and speaker identification (Sarikaya et al, 1998). These applications use respectively 21 subbands (Fig.…”

Section: Inverse Transformationmentioning

confidence: 99%

Wavelet speech enhancement based on time–scale adaptation

Bahoura

Rouat

2006

Speech Communication

View full text Add to dashboard Cite

We propose a new speech enhancement method based on time and scale adaptation of wavelet thresholds. The time dependency is introduced by approximating the Teager Energy of the wavelet coefficients, while the scale dependency is introduced by extending the principle of level dependent threshold to Wavelet Packet Thresholding.This technique does not require an explicit estimation of the noise level or of the apriori knowledge of the SNR, as is usually needed in most of the popular enhancement methods. Performance of the proposed method is evaluated on speech recorded in real conditions (plane, sawmill, tank, subway, babble, car, exhibition hall, restaurant, street, airport, and train station) and artificially added noise. MELscale decomposition based on wavelet packets is also compared to the common wavelet packet scale.Comparison in terms of Signal-to-Noise Ratio (SNR) is reported for time adaptation and time-scale adaptation thresholding of the wavelet coefficients thresholding. Visual inspection of spectrograms and listening experiments are also used to support the results. Hidden Markov Models Speech recognition experiments are conducted on the AURORA-2 database and show that the proposed method improves the speech recognition rates for low SNRs.

show abstract

Teager energy based feature parameters for speech recognition in car noise

Cited by 96 publications

References 11 publications

Real Time Recognition of Elderly Daily Activity using Fuzzy Logic through Fusion of Motion and Location Data

Real Time Recognition of Elderly Daily Activity using Fuzzy Logic through Fusion of Motion and Location Data

Voice Activity Detection Using Global Speech Absence Probability Based on Teager Energy for Speech Enhancement

Wavelet speech enhancement based on time–scale adaptation

Contact Info

Product

Resources

About