Improved voice activity detection based on a smoothed statistical likelihood ratio

Ensemble of deep neural networks using acoustic environment classification for statistical model-based voice activity detection

In this paper, we present an approach to incorporate discriminative weight training into a statistical model-based voice activity detection (VAD) method. In our approach, the VAD decision rule is derived from the optimally weighted likelihood ratios (LRs) using a minimum classification error (MCE) method. An adaptive on-line means of selecting two kinds of weights based on a power spectral flatness measure (PSFM) is devised for performance improvement. The proposed approach is compared to conventional schemes under various noise conditions, and shows better performance.

To obtain reliable performance of Voice Activity Detector (VAD) algorithm, the straight lines on spectrogram of speech-activity being robust against noise is characterized by an entropy-based measure in this paper. A measure of entropy will be defined on the energy domain of harmonic subband. It is shown that the entropy-based measure is well suited for detecting speech in white or quasi-white noises, but will perform poorly for coloured noises. To compensate the limitation, the refined minima controlled recursive averaging, which be updated quickly and accurately even given rapidly increasing levels of noise, is required to desensitize the measure of entropy to various types of noise. Consequently, the proposed VAD algorithm is shown significantly outperform the commonly used energy-based algorithm when SNR drops rapidly, and moreover is insensitive to the changing-level of noise. Experimental results demonstrate that the performance of the proposed VAD is comparable to modern standard VADs such that ITU-T G.729B and ETSI front-end VAD or statistical model-based VADs.

In this paper, a robust multiple observation likelihood ratio test (MOLRT) based voice activity detection (VAD) method is proposed. At the beginning of this paper, we introduce the Wiener filter to the observed signal in time domain which can help mitigating some noise. The reason why we use the Wiener filter for VAD is that the performance of the VAD is always better in high signal to noise ratio (SNR) range than in low SNR range. Then, some ideas are proposed to improve the performance of the MOLRT based VAD method. As we all know, a conventional MOLRT based method including three modules named likelihood ratio (LR) estimation, threshold setting and hangover technique. To improve the estimation accuracy of LR, we adopt the unbiased minimum mean-square error (MMSE) algorithm for noise power spectrum estimation in every frame, which is very effective for LR estimation in MOLRT-based VAD method. That is because the LR is a function of a prior and a posterior SNR and unbiased MMSE algorithm is very useful for noise estimation. In addition, to make our VAD method more robust, a dynamic threshold setting technique is proposed in our method, which is related to the minimum noise power spectrum. That is because minimum noise power spectrum can help us updating the value of threshold to a suitable level according to the denoised signal. Last but most important, a novel hangover algorithm is introduced in this paper comparing to the conventional HMM based hangover algorithm. In the novel hangover algorithm, the current frame is determined by the statistical result of the following speech/non-speech detections based on the likelihood ratio test. And the evaluation results reveal that proposed method significantly outperform the baseline result of LRT as regards VAD accuracy in both noise variations and low SNR conditions.

Publication in the conference proceedings of EUSIPCO, Florence, Italy, 2006

A novel technique is proposed to improve the performance of voice activity detection (VAD) by using deep belief networks (DBN) with a likelihood ratio (LR). The likelihood ratio is derived from the speech and noise spectral components that are assumed to follow the Gaussian probability density function (PDF). The proposed algorithm employs DBN learning in order to classify voice activity by using the input signal to calculate the likelihood ratio. Experiments show that the proposed algorithm yields improved results in various noise environments, compared to the conventional VAD algorithms. Furthermore, the DBN based algorithm decreases the detection probability of error with [0.7, 2.6] compared to the support vector machine based algorithm.

In recent years, DNN-based systems are extremely popular for performing automatic speech recognition (ASR) task. They have shown better performance than other methods. To perform ASR task efficiently, segmentation of the input data also has to be accurate. There are different kinds of methods of voice activity detection (VAD) including power based statistical methods. But to incorporate with the ASR system, it is better to perform the VAD task with the help of DNN-based method. In this paper, we investigate the superiority of DNN-based VAD over power based statistical methods. Not only that but also the effect of data augmentation on the performance of VAD in various conditions is also investigated. Performance of the VAD is evaluated using CENSREC-1-C data especially developed for evaluation of VAD task. The VAD trained with multi-condition data shows better performance than the baseline and other popular power based statistical VAD tools. We have also evaluated the performance for eval1 test dataset of CSJ corpus as well as its telephone variants.

This paper presents a new method for voice activity detection (VAD) based on the autoregressive-generalized autoregressive conditional heteroscedasticity (AR-GARCH) model. The speech signal is modeled as an AR-GARCH process in the time domain, and the likelihood ratio is computed and compared to a threshold. The time-varying variance of the speech signal needed for computing the likelihood function under speech presence hypothesis, is estimated using the AR-GARCH model. The model parameters are estimated using a novel technique based on the recursive maximum likelihood (RML) estimation. The variance of the additive noise, a critical issue in designing a VAD, is estimated using the improved minima controlled recursive averaging (IMCRA) method, which is properly modified to be applicable to noise variance estimation in the time domain. The performances of the VAD and the parameter estimation method are examined under several conditions. Experimental results indicate the robustness of the AR-GARCH based VAD both to noise variations and low signal-to-noise ratio (SNR) conditions.

We present an approach to model-based voice activity detection (VAD) for harsh environments. By using mel-frequency cepstral coefficients feature extracted from clean and noisy speech samples, an artificial neural network is trained optimally in order to provide a reliable model. There are three main aspects to this study: First, in addition to the developed model, recent state-of-the-art VAD methods are analyzed extensively. Second, we present an optimization procedure of neural network training, including evaluation of trained network performance with proper measures. Third, a large assortment of empirical results on the noisy TIMIT and SNOW corpuses including different types of noise at different signal-to-noise ratios is provided. We evaluate the built VAD model on the noisy corpuses and compare against the state-of-the-art VAD methods such as the ITU-T Rec. G. 729 Annex B, the ETSI AFE ES 202 050, and recently promising VAD algorithms. Results show that: (i) the proposed neural network classifier employing MFCC feature provides robustly high scores under different noisy conditions; (ii) the invented model is superior to other VAD methods in terms of various classification measures; (iii) the robustness of the developed VAD algorithm is still hold in the case of testing it with the completely mismatched environment.

Statistical likelihood ratio test is a widely used voice activity detection (VAD) method, in which the likelihood ratio of the current temporal frame is compared with a threshold. A fixed threshold is always used, but this is not suitable for various types of noise. In this paper, an adaptive threshold is proposed as a function of the local statistics of the likelihood ratio. This threshold represents the upper bound of the likelihood ratio for the non-speech frames, whereas it remains generally lower than the likelihood ratio for the speech frames. As a result, a high non-speech hit rate can be achieved, while maintaining speech hit rate as large as possible.

We introduce an efficient hidden Markov model-based voice activity detection (VAD) algorithm with time-variant state-transition probabilities in the underlying Markov chain. The transition probabilities vary in an exponential charge/discharge scheme and are softly merged with state conditional likelihood into a final VAD decision. Working in the domain of ITU-T G.729 parameters, with no additional cost for feature extraction, the proposed algorithm significantly outperforms G.729 Annex B VAD while providing a balanced tradeoff between clipping and false detection errors. The performance compares very favorably with the adaptive multi-rate VAD, option 2 (AMR2).

In this paper, a novel approach to apply GM(1,1) model in voice activity detection (VAD) is presented. The approach is termed as grey VAD (GVAD). In GVAD, GM(1,1) model is used to estimate noise in noisy speech and therefore signal where the additive signal model is assumed. By estimated noise and signal, the signal-to-noise ratio (SNR) is calculated. Based on an adaptive threshold, speech and non-speech segments are determined. The proposed GVAD is performed in the time-domain and thus has low computational complexity. In the simulation, GVAD is verified by cases with non-stationary additive white Gaussian noise and is compared with VAD in G 729 and GSM AMR. The results indicate that the proposed GVAD is able to detect voice activity appropriately. In the given examples, the performance of GVAD is better than VAD in G 729 and GSM AMR.

Improved likelihood ratio test based voice activity detector applied to speech recognition

A robust algorithm for voice activity detection (VAD) is presented. It defines a likelihood ratio test (LRT) involving multiple and independent observations of the bispectra. The proposed VAD provides significant improvements in speech/pause discrimination when compared to standardised and recently reported VADs.

Analysis of derivative of instantaneous frequency and its application to voice activity detection