Proposed Voice Activity Detection Method Research Articles

Multi-Task Learning U-Net for Single-Channel Speech Enhancement and Mask-Based Voice Activity Detection

In this paper, a multi-task learning U-shaped neural network (MTU-Net) is proposed and applied to single-channel speech enhancement (SE). The proposed MTU-based SE method estimates an ideal binary mask (IBM) or an ideal ratio mask (IRM) by extending the decoding network of a conventional U-Net to simultaneously model the speech and noise spectra as the target. The effectiveness of the proposed SE method was evaluated under both matched and mismatched noise conditions between training and testing by measuring the perceptual evaluation of speech quality (PESQ) and short-time objective intelligibility (STOI). Consequently, the proposed SE method with IRM achieved a substantial improvement with higher average PESQ scores by 0.17, 0.52, and 0.40 than other state-of-the-art deep-learning-based methods, such as the deep recurrent neural network (DRNN), SE generative adversarial network (SEGAN), and conventional U-Net, respectively. In addition, the STOI scores of the proposed SE method are 0.07, 0.05, and 0.05 higher than those of the DRNN, SEGAN, and U-Net, respectively. Next, voice activity detection (VAD) is also proposed by using the IRM estimated by the proposed MTU-Net-based SE method, which is fundamentally an unsupervised method without any model training. Then, the performance of the proposed VAD method was compared with the performance of supervised learning-based methods using a deep neural network (DNN), a boosted DNN, and a long short-term memory (LSTM) network. Consequently, the proposed VAD methods show a slightly better performance than the three neural network-based methods under mismatched noise conditions.

Noise Robust Voice Activity Detection Based on Multi-Layer Feed-Forward Neural Network

DOI: 10.26650/electrica.2019.18042 This paper proposes a voice activity detection (VAD) method based on time and spectral domain features using multi-layer feed-forward neural network (MLF-NN) for various noisy conditions. In the proposed method, time features that were short-time energy and zero-crossing rate and spectral features that were entropy, centroid, roll-off, and flux of speech signals were extracted. Clean speech signals were used in training MLF-NN and the network was tested for noisy speech at various noisy conditions. The proposed VAD method was evaluated for six kinds of noises which are white, car, babble, airport, street, and train at four different signal-to-noise ratio (SNR) levels. The proposed method was tested on core TIMIT database and its performance was compared with SOHN, G.729B and Long-Term Spectral Flatness (LSFM) VAD methods in point of correct speech rate, false alarm rate, and overall accuracy rate. Extensive simulation results show that the proposed method gives the most successful average correct speech rate, false alarm rate, and overall accuracy rate in most low and high SNR level conditions for different noise environments. Cite this article as : Arslan O, Engin EZ. Noise Robust Voice Activity Detection Based on Multi-Layer Feed-Forward Neural Network. Electrica 2019; 10.26650/electrica.2019.18042.

Voice Activity Detection Using Fuzzy Entropy and Support Vector Machine

This paper proposes support vector machine (SVM) based voice activity detection using FuzzyEn to improve detection performance under noisy conditions. The proposed voice activity detection (VAD) uses fuzzy entropy (FuzzyEn) as a feature extracted from noise-reduced speech signals to train an SVM model for speech/non-speech classification. The proposed VAD method was tested by conducting various experiments by adding real background noises of different signal-to-noise ratios (SNR) ranging from −10 dB to 10 dB to actual speech signals collected from the TIMIT database. The analysis proves that FuzzyEn feature shows better results in discriminating noise and corrupted noisy speech. The efficacy of the SVM classifier was validated using 10-fold cross validation. Furthermore, the results obtained by the proposed method was compared with those of previous standardized VAD algorithms as well as recently developed methods. Performance comparison suggests that the proposed method is proven to be more efficient in detecting speech under various noisy environments with an accuracy of 93.29%, and the FuzzyEn feature detects speech efficiently even at low SNR levels.

Voice activity detection based on conjugate subspace matching pursuit and likelihood ratio test

Most of voice activity detection (VAD) schemes are operated in the discrete Fourier transform (DFT) domain by classifying each sound frame into speech or noise based on the DFT coefficients. These coefficients are used as features in VAD, and thus the robustness of these features has an important effect on the performance of VAD scheme. However, some shortcomings of modeling a signal in the DFT domain can easily degrade the performance of a VAD in a noise environment. Instead of using the DFT coefficients in VAD, this article presents a novel approach by using the complex coefficients derived from complex exponential atomic decomposition of a signal. With the goodness-of-fit test, we show that those coefficients are suitable to be modeled by a Gaussian probability distribution. A statistical model is employed to derive the decision rule from the likelihood ratio test. According to the experimental results, the proposed VAD method shows better performance than the VAD based on the DFT coefficients in various noise environments.

Online Unsupervised Classification With Model Comparison in the Variational Bayes Framework for Voice Activity Detection

A new online, unsupervised method for Voice Activity Detection (VAD) is proposed. The conventional VAD methods often rely on heuristics to adapt the decision threshold to the estimated SNR. The proposed VAD method is based on the Variational Bayes (VB) approach to the online Expectation Maximization (EM), so that it can automatically adapt the decision level and the statistical model at the same time. We consider two parallel classifiers, one for the noise-only case, and the other for speech-and-noise case. Both models are trained concurrently and online using the VB framework. The VB framework also provides an explicit approximation of the log evidence called free energy. It is used to assess the reliability of the classifier in an online fashion, and to decide which model is more appropriate at a given time frame. Experimental evaluations were conducted on the CENSREC-1-C database designed for VAD evaluations. With the effect of the model comparison, the proposed scheme outperforms the conventional VAD algorithms, especially in the remote recording condition. It is also shown to be more robust with respect to changes of the noise type.

Voice activity detection based on adjustable linear prediction and GARCH models

We propose a method for voice activity detection (VAD) that employs a class of the Autoregressive–Generalized Autoregressive Conditional Heteroskedasticity (AR-GARCH) model. As regards correlated speech signals, we represent the AR part of the AR-GARCH model with a state-space to obtain the appropriate linear prediction error series. By applying the GARCH model to the residual, we estimate the conditional variance sequences corresponding to the voice activity parts. To detect voice activity, we establish an appropriate threshold for the conditional variance sequences. To confirm the performance of our proposed VAD method, we conduct experiments using speech signals with real background noise (signal-to-noise ratios (SNRs) of 10, 5 and 0 dB) of an airport and a street. Furthermore, using receiver operating characteristics curves and equal error rates, we compare our results with those of previous standardized VAD algorithms (ITU-T G.729B, ETSI ES 202 050, and ETSI EN 301 708) as well as recently developed methods (VAD with long-term spectral divergence, likelihood ratio tests, and higher-order statistics for VAD). In terms of the signals with background noise at an SNR of 0 dB, the experimental results show a significant performance improvement compared with standardized VAD algorithms and more than 10% improvement compared with recently developed VAD methods.

Speech Waveform Compression Using Robust Adaptive Voice Activity Detection for Nonstationary Noise

The voice activity detection (VAD) is crucial in all kinds of speech applications. However, almost all existing VAD algorithms suffer from the nonstationarity of both speech and noise. To combat this difficulty, we propose a new voice activity detector, which is based on the Mel-energy features and an adaptive threshold related to the signal-to-noise ratio (SNR) estimates. In this paper, we first justify the robustness of the Bayes classifier using the Mel-energy features over that using the Fourier spectral features in various noise environments. Then, we design an algorithm using the dynamic Mel-energy estimator and the adaptive threshold, which depends on the SNR estimates. In addition, a realignment scheme is incorporated to correct the sparse-and-spurious noise estimates. Numerous simulations are carried out to evaluate the performance of our proposed VAD method and the comparisons are made with a couple of existing representative schemes, namely, the VAD using the likelihood ratio test with Fourier spectral energy features and that based on the enhanced time-frequency parameters. Three types of noises, namely, white noise (stationary), babble noise (nonstationary), and vehicular noise (nonstationary) were artificially added by the computer for our experiments. As a result, our proposed VAD algorithm significantly outperforms other existing methods as illustrated by the corresponding receiver operating characteristics (ROC) curves. Finally, we demonstrate one of the major applications, namely, speech waveform compression associated with our new robust VAD scheme and quantify the effectiveness in terms of compression efficiency.