Energy-based Voice Activity Detection Research Articles

Examination of Energy Based Voice Activity Detection Algorithms for Noisy Speech Signals

This paper examines the behavior of two different energy-based voice activity detector (VAD) algorithms for noisy input signals. The examined detectors use time-domain methods to find speech boundaries. Time-domain short time energy features and/or zero-crossing rate of speech signals are used to evaluate the performance of the methods. In the first stage of both algorithms, time-domain short-time energy (STE) features are calculated for each speech segment. Then energy ratios and threshold values are used to detect any voicing activity of speech signals. The decision threshold value is calculated by evaluating the average STE of an initial silence period. The effectiveness of the selected methods is tested for clean and noisy speech samples. The methods are tested using the noisy speech signals under different SNR levels. The results indicated that both methods achieve a reasonable accuracy as low as an SNR value nearly 0dB with a slowly decreasing performance. But, under 0dB SNR, both methods lose their effectiveness against noisy conditions.

Wavelet energy based voice activity detection and adaptive thresholding for efficient speech coding

During the last five decades, extensive researches have been carried out in the field of speech compression, which has resulted in various techniques for speech coding. Researchers have been in full swing for more efficient speech coding and their effort is still continuing in different parts of the world. In this paper we are proposing an alternative method for better speech coding. In the proposed technique we use discrete wavelet transform to decompose the signal and wavelet energy is used to differentiate between active voice region and silence region in the speech signal. Depending upon the region’s status the system, different thresholding strategies have been chosen which leads to a better compression without any loss of speech intelligibility. The proposed method is evaluated in terms of qualitative and quantitative parameters. In this paper we also propose an alternative parameter for MOS values which is here after known as System Recognition Rate.

Speaker Verification Under Degraded Conditions Using Empirical Mode Decomposition Based Voice Activity Detection Algorithm

AbstractThe performance of most of the state-of-the-art speaker recognition (SR) systems deteriorates under degraded conditions, owing to mismatch between the training and testing sessions. This study focuses on the front end of the speaker verification (SV) system to reduce the mismatch between training and testing. An adaptive voice activity detection (VAD) algorithm using zero-frequency filter assisted peaking resonator (ZFFPR) was integrated into the front end of the SV system. The performance of this proposed SV system was studied under degraded conditions with 50 selected speakers from the NIST 2003 database. The degraded condition was simulated by adding different types of noises to the original speech utterances. The different types of noises were chosen from the NOISEX-92 database to simulate degraded conditions at signal-to-noise ratio levels from 0 to 20 dB. In this study, widely used 39-dimension Mel frequency cepstral coefficient (MFCC; i.e., 13-dimension MFCCs augmented with 13-dimension velocity and 13-dimension acceleration coefficients) features were used, and Gaussian mixture model–universal background model was used for speaker modeling. The proposed system’s performance was studied against the energy-based VAD used as the front end of the SV system. The proposed SV system showed some encouraging results when EMD-based VAD was used at its front end.

Energy-based VAD with grey magnitude spectral subtraction

In this paper, we propose a novel voice activity detection (VAD) scheme for low SNR conditions with additive white noise. The proposed approach consists of two parts. First, a grey magnitude spectral subtraction (GMSS) is applied to remove additive noise from a given noisy speech. By this doing, an estimated clean speech is obtained. Second, the enhanced speech by the GMSS is segmented and put into an energy-based VAD to determine whether it is a speech or non-speech segment. The approach presented in this paper is called the GMSS/EVAD. Simulation results indicate that the proposed GMSS/EVAD outperforms VAD in G.729 and GSM AMR for the given low SNR examples. To investigate the performance of the GMSS/EVAD for real-life background noises, the babble and volvo noises in the NOISEX-92 database are under consideration. The simulation results for the given examples indicate that the GMSS/EVAD is able to handle appropriately for the cases of the babble noise with the SNR above 10 dB and the cases of the volvo noise with SNR 15 dB and up.

Frequency-domain criterion for the speech distortion weighted multichannel Wiener filter for robust noise reduction

Recently, a generalized multi-microphone noise reduction scheme, referred to as the spatially pre-processed speech distortion weighted multichannel Wiener filter (SP-SDW-MWF), has been presented. This scheme consists of a fixed spatial pre-processor and a multichannel adaptive noise canceler (ANC) optimizing the SDW-MWF cost function. By taking speech distortion explicitly into account in the design criterion of the multichannel ANC, the SP-SDW-MWF adds robustness to the standard generalized sidelobe canceler (GSC). In this paper, we present a multichannel frequency-domain criterion for the SDW-MWF, from which several – existing and novel – adaptive frequency-domain algorithms can be derived. The main difference between these adaptive algorithms consists in the calculation of the step size matrix (constrained vs. unconstrained, block-structured vs. diagonal) used in the update formula for the multichannel adaptive filter. We investigate the noise reduction performance, the robustness and the tracking performance of these adaptive algorithms, using a perfect voice activity detection (VAD) mechanism and using an energy-based VAD. Using experimental results with a small-sized microphone array in a hearing aid, it is shown that the SP-SDW-MWF is more robust against signal model errors than the GSC, and that the block-structured step size matrix gives rise to a faster convergence and a better tracking performance than the diagonal step size matrix, only at a slightly higher computational cost.