Voice Activity Detection Decision Research Articles

Hybrid voice activity detection system based on LSTM and auditory speech features

Voice Activity Detection (VAD), sometimes called as Speech Activity Detection, is the process of extracting speech regions in audio recordings including many type of sounds. Because undesired data causes both computational complexity and time wasting, most of speech based applications consider only speech part (region of interest) and ignore the rest. This is the main reason that makes usage of the VAD stands a preliminary stage in applications like automatic speech recognition (ASR), speaker identification/verification, speech enhancement, speaker diarization etc. In this study, a successful semi-supervised VAD system, which we named as “hybridVAD”, was proposed especially for the environment with high signal-to-noise ratio (SNR) with the manner of two-stage. At first, VAD decision was obtained from a relatively simple Long-Short Term Memory (LSTM) network trained by auditory speech features like energy, zero crossing rate (ZCR) and 13rd order-Mel Frequency Cepstral Coefficients (MFCC). After we applied a reasonable thresholding strategy to the same features to have second VAD decision, we combined both decisions with logical operators. The result was surprisingly showed that final VAD decision have low FEC and OVER errors, which are specifically critical for any speaker diarization system, mostly in the environments with high SNR.

Real Time Implementation of Voice Activity Detection based on False Acceptance Regulation

In speech compression systems, Voice Activity Detection (VAD) is frequently used to distinguish active voice from other noisy sounds. In this paper, a robust approach of VAD is presented to deal with non-stationary noisy environments. The proposed algorithm exploits adaptive thresholding technique to keep a desired False Acceptance (FA) rate. Iterative hypothesis tests, using signal energy, are implemented to discard or to accept the successive audio frames as active voice. According to the stationary property of the speech, we provide a smoothing method to obtain final VAD decisions. The main contribution of the proposed algorithm concerns its ability to automatically adjust the energy threshold according to the local noise estimator. We analyzed the proposed approach by presenting a comparison with the G.729-B via the NOIZEUS database. The VAD architecture is implemented on a Microcontroller-based system (MCU). Several tests have been conducted by performing real time acquisition via the Input/Output ports of the MCU-system.

Unsupervised and supervised VAD systems using combination of time and frequency domain features

Voice Activity Detection (VAD), also referred as Speech Activity Detection (SAD) is the process of identifying speech/non-speech region in digital speech recordings. It is used as a preliminary stage to reduce errors and increase effectiveness in the most of speech based applications like automatic speech recognition (ASR), speaker identification/verification, speech enhancement, speaker diarization etc. In this study, two independent VAD structures were proposed for unsupervised and supervised approaches using both time and frequency domain features. The autocorrelation based pitch contour estimation was used together with the 1NN Cosine classifier trained by 21-column feature matrix comprising Energy, Zero Crossing Rate (ZCR), 13rd order-Mel Frequency Cepstral Coefficients (MFCC) and Shannon Entropies of daubechies-filtered 5th depth-Wavelet Packet Transform (WPT) to obtain VAD decision in supervised approach, while methods like normalization, thresholding and median filtering were applied over the same feature set in unsupervised approach. The proposed unsupervised VAD achieved error rates of 4%, 19%, 0.02% and 0.7% for the FEC, MSC, OVER and NDS, respectively at 0 dB SNR. The VAD decisions of both supervised and unsupervised systems showed that the proposed methods can efficiently be used either in silent or in environments with noise similar to Additive White Gaussian Noise (AWGN).

Enhancement of speech dynamics for voice activity detection using DNN

Voice activity detection (VAD) is an important preprocessing step for various speech applications to identify speech and non-speech periods in input signals. In this paper, we propose a deep neural network (DNN)-based VAD method for detecting such periods in noisy signals using speech dynamics, which are time-varying speech signals that may be expressed as the first- and second-order derivatives of mel cepstra, also known as the delta and delta-delta features. Unlike these derivatives, in this paper, the dynamics are highlighted by speech period candidates, which are calculated based on heuristic rules for the patterns of the first and second derivatives of the input signals. These candidates, together with the log power spectra, are input into the DNN to obtain VAD decisions. In this study, experiments are conducted to compare the proposed method with a DNN-based method, which exclusively utilizes log power spectra by using speech signals smeared with five types of noise (white, babble, factory, car, and pink) with signal-to-noise ratios (SNRs) of 10, 5, 0, and − 5 dB. The experimental results show that the proposed method is superior under all the considered noise conditions, indicating that the speech period candidates improve the log power spectra.

Improvements on self-adaptive voice activity detector for telephone data

Voice activity detection (VAD) has been studied for many decades and energy VAD is most commonly used. Energy VAD performs well under noise-free environments but deteriorates under noisy environment. Self-adaptive VAD performs much better than the traditional energy VAD in many aspects. However, one issue is that, the single one minimum energy threshold of the self-adaptive AVD could not perform well under the conditions with different channel varieties or background noises. In this paper, we make several improvements on the self-adaptive VAD to deal with that issue and enhance the detection performances. A k-means based average energy clustering approach is proposed to find better minimum energy thresholds for each speech recording. In the VAD decision phase, the new threshold is used for the likelihood ratio test. Furthermore, better results have been achieved by applying the median filtering as a post-processing step of self-adaptive VAD to smooth the short-time noise VAD errors. Experimental results on a subset of the NIST 2006 speaker recognition evaluation dataset show that our proposed method outperforms both the traditional energy-based and self-adaptive VAD approaches.

Optimally weighted maximum a posteriori probabilities based on minimum classification error for dual-microphone voice activity detection

The dual-microphone voice activity detection (VAD) technique is proposed by applying discriminative weight training to achieve optimal weighting of spatial features available within the dual-microphone VAD. Since the motivation behind our method is to use the relevant spatial information available from the two microphones, we employ the phase difference, coherence, and power level difference ratio (PLDR) as a feature vector, and then use this feature vector to derive the maximum a posteriori (MAP) probabilities. Then, we combine each MAP probability based on a discriminative weight training, i.e., the minimum classification error (MCE) method to offer an optimal VAD decision in a spectral domain, which successfully represents the dynamic evolution of speech over time even in the non-stationary noise environments. The proposed dual-microphone VAD algorithm outperforms conventional dual-microphone VAD methods based on only single feature among the PLDR, phase difference, and spectral coherence.

비정체성 잡음을 위한 SPD-TE 기반 계수형 음성 활동 탐지

A single channel VAD (Voice Activity Detection) algorithm for nonstationary noise environment is proposed in this paper. Threshold values of the feature parameter for VAD decision are updated adaptively based on estimates of means and standard deviations of past non-speech frames. The feature parameter, SPD-TE (Spectral Power Difference-Teager Energy), is obtained by applying the Teager energy to the WPD (Wavelet Packet Decomposition) coefficients. It was reported previously that the SPD-TE is robust to noise as a feature for VAD. Experimental results by using TIMIT speech and NOISEX-92 noise databases show that decision accuracy of the proposed algorithm is comparable to several typical VAD algorithms including standards for SNR values ranging from 10 to -10 dB.

Voice activity detection system for smart earphones

This paper presents a real-time voice activity detection (VAD) algorithm implemented in a miniature Digital Signal Processor (DSP) for in-ear listening devices such as earphones or headphones. This system allows consumers to hear external speech signals such as public announcements or oral communication while listening to music without removing their listening devices. The proposed algorithm uses two normalized energy features that compare the energy in the frequency region containing speech information with the frequency regions typically containing noise. The extraction of the normalized features represents the key of the proposed VAD since it eliminates the need for a signal-to-noise ratio (SNR) estimator. The VAD's decision is made using two threshold comparison rules computed from the normalized features and a hangover scheme triggered after a given number of observations. The algorithm parameters, namely the frequency regions' boundaries, number of observations, two decision thresholds and hangover's duration, have been optimized offline using a genetic algorithm. The performance of the proposed VAD is compared to a benchmark algorithm in four noise environments and three SNRs. Results show that the average false positive rate (FPR) of the proposed algorithm is 4.2% and the average true positive rate (TPR) is 91.4 % compared to the benchmark algorithm which has a FPR average of 29.9 % and a TPR average of 79.0 %. The proposed VAD is implemented in hardware to validate its reliability and complexity.

Dual-Microphone Voice Activity Detection Technique Based on Two-Step Power Level Difference Ratio

In this paper, we propose a novel dual-microphone voice activity detection (VAD) technique based on the two-step power level difference (PLD) ratio. This technique basically exploits the PLD between the primary microphone and the secondary microphone in a mobile device when the distance between the microphones and the sound source is relatively short. Based on the PLD, we propose the use of the PLD ratio (PLDR) instead of the original PLD to take advantage of the relative difference between the PLD of speech and the PLD of noise. Indeed, the PLDR is obtained by estimating the ratio of the PLD between the input signals and the PLD between the two channel noises during periods without speech. The proposed technique offers a two-step algorithm using the PLDRs including long-term PLDR (LT-PLDR), which characterizes long-term evolution and short-term PLDR (ST-PLDR), which characterizes short-time variation during the first step. LT-PLDR-based and ST-PLDR-based VAD decision are performed using the maximum a posteriori (MAP) probability derived from the model-trust algorithm and combined at the second step to reach a superior VAD decision for both long-term and short-term situations. Extensive experimental results show that the proposed dual-microphone VAD technique outperforms the conventional two-channel VAD method as well as most standardized VAD algorithms.

Voice activity detection algorithm using perceptual wavelet entropy neighbor slope.

This paper presents a voice activity detection (VAD) approach using a perceptual wavelet entropy neighbor slope (PWENS) in a low signal-to-noise (SNR) environment and with a variety of noise types. The basis for our study is to use acoustic features that have large entropy variance for each wavelet critical band. The speech signal is decomposed by the proposed perceptual wavelet packet decomposition (PWPD), and the VAD function is extracted by PWENS. Finally, VAD is decided by the proposed VAD decision rule using two memory buffers. In order to evaluate the performance of the VAD decision, many speech samples and a variety of SNR conditions were used in the experiment. The performance of the VAD decision is confirmed using objective indexes such as a graph of the VAD decision and the relative error rate.

조건 사후 최대 확률과 음성 스펙트럼 변이 조건을 이용한 통계적 모델 기반의 음성 검출기

본 논문에서는 조건 사후 최대 확률 (conditional maximum a posteriori, CMAP)과 음성 스펙트럼 변이 조건을 기반으로 한 새로운 음성 검출기 (voice activity detection, VAD)를 제안한다. 제안된 음성 검출기는 통계적 모델을 기반으로 한 우도비 테스트 (likelihood ratio test, LRT)의 문턱값을 결정하는데 조건 사후 최대 확률과 스펙트럼 변이의 상태 값을 조건부 확률로 부과한다. 제안된 알고리즘을 다양한 잡음 환경에서 기존의 CMAP 기반의 음성 검출기와 비교한 결과 전체적으로 향상된 성능을 보였으며 특히 SNR이 낮은 조건에서 향상 폭이 컸다. In this paper, we propose a novel approach to improve the performance of a statistical model-based voice activity detection (VAD) which is based on the conditional maximum a posteriori (CMAP) with deviation. In our approach, the VAD decision rule is expressed as the geometric mean of likelihood ratios (LRs) based on adapted threshold according to the speech presence probability conditioned on both the speech activity decisions and spectral deviation in the pervious frame. Experimental results show that the proposed approach yields better results compared to the CMAP-based VAD using the LR test.

Voice Activity Detection for Speech Enhancement Applications

This paper describes a study of noise-robust voice activity detection (VAD) utilizing the periodicity of the signal, full band signal energy and high band to low band signal energy ratio. Conventional VADs are sensitive to a variably noisy environment especially with low SNR, and also result in cutting off unvoiced regions of speech as well as random oscillating of output VAD decisions. To overcome these problems, the proposed algorithm first identifies voiced regions of speech and then differentiates unvoiced regions from silence or background noise using the energy ratio and total signal energy. The performance of the proposed VAD algorithm is tested on real speech signals. Comparisons confirm that the proposed VAD algorithm outperforms the conventional VAD algorithms, especially in the presence of background noise.

Voice Activity Detection Based on Discriminative Weight Training Incorporating a Spectral Flatness Measure

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.

Improved voice activity detection algorithm using wavelet and support vector machine

This paper proposes an improved voice activity detection (VAD) algorithm using wavelet and support vector machine (SVM) for European Telecommunication Standards Institution (ETSI) adaptive multi-rate (AMR) narrow-band (NB) and wide-band (WB) speech codecs. First, based on the wavelet transform, the original IIR filter bank and pitch/tone detector are implemented, respectively, via the wavelet filter bank and the wavelet-based pitch/tone detection algorithm. The wavelet filter bank can divide input speech signal into several frequency bands so that the signal power level at each sub-band can be calculated. In addition, the background noise level can be estimated in each sub-band by using the wavelet de-noising method. The wavelet filter bank is also derived to detect correlated complex signals like music. Then the proposed algorithm can apply SVM to train an optimized non-linear VAD decision rule involving the sub-band power, noise level, pitch period, tone flag, and complex signals warning flag of input speech signals. By the use of the trained SVM, the proposed VAD algorithm can produce more accurate detection results. Various experimental results carried out from the Aurora speech database with different noise conditions show that the proposed algorithm gives considerable VAD performances superior to the AMR-NB VAD Options 1 and 2, and AMR-WB VAD.

Discriminative Weight Training for a Statistical Model-Based Voice Activity Detection

In this letter, we apply a discriminative weight training to a statistical model-based voice activity detection (VAD). In our approach, the VAD decision rule is expressed as the geometric mean of optimally weighted likelihood ratios (LRs) based on a minimum classification error (MCE) method. That approach is different from that of previous works in that different weights are assigned to each frequency bin and is considered to be more realistic. According to the experimental results, the proposed approach is found to be effective for the statistical model-based VAD using the LR test.

A Semi-Continuous State-Transition Probability HMM-Based Voice Activity Detector

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).

Voice Activity Detection Algorithm Based on Radial Basis Function Network

This paper proposes a Voice Activity Detection (VAD) algorithm using Radial Basis Function (RBF) network. The k-means clustering and Least Mean Square (LMS) algorithm are used to update the RBF network to the underlying speech condition. The inputs for RBF are the three parameters a Code Excited Linear Prediction (CELP) coder, which works stably under various background noise levels. Adaptive hangover threshold applies in RBF-VAD for reducing error, because threshold value has trade off effect in VAD decision. The experimental results show that the proposed VAD algorithm achieves better performance than G.729 Annex B at any noise level.

A Computationally Efficient Mel-Filter Bank VAD Algorithm for Distributed Speech Recognition Systems

This paper presents a novel computationally efficient voice activity detection (VAD) algorithm and emphasizes the importance of such algorithms in distributed speech recognition (DSR) systems. When using VAD algorithms in telecommunication systems, the required capacity of the speech transmission channel can be reduced if only the speech parts of the signal are transmitted. A similar objective can be adopted in DSR systems, where the nonspeech parameters are not sent over the transmission channel. A novel approach is proposed for VAD decisions based on mel-filter bank (MFB) outputs with the so-called Hangover criterion. Comparative tests are presented between the presented MFB VAD algorithm and three VAD algorithms used in the G.729, G.723.1, and DSR (advanced front-end) Standards. These tests were made on the Aurora 2 database, with different signal-to-noise (SNRs) ratios. In the speech recognition tests, the proposed MFB VAD outperformed all the three VAD algorithms used in the standards by 14.19% relative (G.723.1 VAD), by 12.84% relative (G.729 VAD), and by 4.17% relative (DSR VAD) in all SNRs.