Voice Activity Detection. Fundamentals and Speech Recognition System Robustness

Combined speech enhancement and auditory modelling for robust distributed speech recognition

A new voice activity detection (VAD) algorithm with soft decision output in Mel-frequency domain is developed based on hidden Markov model (HMM) and is incorporated in an HMM-based speech enhancement system. The proposed VAD uses a two-state ergodic HMM representing speech presence and speech absence. The states are constructed from noisy speech and noise HMMs used in the speech enhancement system. This composite model provides a robust detection of speech segments in the presence of noise and obviates the need for extra modeling in HMM-based speech enhancement applications. As the main purpose of the proposed VAD is to detect speech segments accurately, a hang-over mechanism is proposed and is applied on the output of the VAD to improve the speech detection rate. The VAD is integrated in the HMM-based speech enhancement system in Mel-frequency spectral (MFS) and cepstral (MFC) domains. The performance of the proposed VAD, the effectiveness of the hang-over mechanism and the performance of the VAD-integrated speech enhancement system are evaluated on four noise types at different SNR levels. The experimental results confirm the superiority of the proposed VAD compared to the reference methods particularly for speech detection rate at the dominant noisy conditions.

Accurate and effective voice activity detection (VAD) is a fundamental step for robust speech or speaker recognition. In this study, we proposed a hierarchical framework approach for VAD and speech enhancement. The modified Wiener filter (MWF) approach is utilized for noise reduction in the speech enhancement block. For the feature selection and voting block, several discriminating features were employed in a voting paradigm for the consideration of reliability and discriminative power. Effectiveness of the proposed approach is compared and evaluated to other VAD techniques by using two well-known databases, namely, TIMIT database and NOISEX-92 database. Experimental results show that the proposed method performs well under a variety of noisy conditions.

This paper presents a front-end speech enhancement approach to robust speech recognition in automotive environments. It combines hybrid voice activity detection (VAD), relative transfer function (RT-F) based generalized sidelobe cancelation, and single-channel post filtering to enhance the speech signal of interest, thereby improving the robustness of speech recognition. First, we choose four typical driving scenarios, which include most of the noise types in automobiles to record training data. The recorded data is then used to train deep neural network models (DNNs) for both speech and noise. The trained DNNs are subsequently used to estimate the speech presence probability on a frame-by-frame basis. This speech presence probability is then combined with the output of an energy-based VAD to form a hybrid VAD, which serves as the basis for the rest components of the speech enhancement system, including RTF estimation, adaptive beamforming, and post-filtering. Experiments are conducted in real automotive environments. The results show that the developed method can significantly improve the performance of both VAD and automatic speech recognition (ASR).

Voice activity detection (VAD) is an outstanding problem for speech transmission, enhancement and recognition. The variety and the varying nature of speech and background noise make it especially challenging. In the past years, many features emphasizing the differences between speech and noise have been proposed for their robustness. However an important problem in many areas of speech processing is the determination of presence of speech periods in a given signal. This task can be identified as a statistical hypothesis problem and its purpose is the determination to which category or class a given signal belongs. Also the classification task is often not as trivial as it appears since the increasing level of background noise leading to numerous detection errors. The selection of an adequate feature vector for signal detection and a robust decision rule is a challenging problem that affects the performance of VADs. Most algorithms are effective in numerous applications but often cause detection errors mainly due to the loss of discriminating power of the decision rule at lower SNRs. In this paper, it has been tried to extract the characteristics of noise by the VAD algorithm which can be used to smooth out the signal in silence part from the noisy environment. For further noise reduction signal then filtered in the wavelet domain using thresholding.

This paper presents the behavioural mechanism of a statistical model-based voice activity detector (VAD), featuring a likelihood ratio test for the activity decision. From investigation of the VAD, it is found that detection errors could occur frequently at speech offset regions because of the delay term in the decision-directed parameter estimator, employed for the estimation of an unknown parameter of the likelihood ratio. Hence, this paper proposes a smoothed likelihood ratio so as to alleviate the detection errors at the offset region. Objective test results show that the proposed scheme is useful for achieving a considerable performance improvement for the VAD. Additionally, the proposed VAD gives detection performances superior to G.729B VAD and comparable with the AMR VAD option 2.

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

This paper describes the VAD (voice activity detection) for controlling DTX (discontinuous transmission) of the GSM AMR (adaptive multi-rate) speech codec. The algorithm is based on spectral estimation and periodicity detection. The VAD contains a 9-band IIR filter bank, which divides input signals into frequency bands. The signal level at each band is calculated. Background noise is estimated in each sub-band. The VAD decision is computed by comparing input signal level and background noise estimate. The algorithm incorporates novel methods to estimate background noise and to detect periodic components based on open-loop pitch gain. A new method is also derived to detect correlated complex signals like music.

Two of the major challenges in microphone array based adaptive beamforming, speech enhancement and distant speech recognition, are robust and accurate source localization and voice activity detection. This paper introduces a spatial gradient steered response power using the phase transform (SRP-PHAT) method which is capable of localization of competing speakers in overlapping conditions. We further investigate the behavior of the SRP function and characterize theoretically a fixed point in its search space for the diffuse noise field. We call this fixed point the null position in the SRP search space. Building on this evidence, we propose a technique for multichannel voice activity detection (MVAD) based on detection of a maximum power corresponding to the null position. The gradient SRP-PHAT in tandem with the MVAD form an integrated framework of multi-source localization and voice activity detection. The experiments carried out on real data recordings show that this framework is very effective in practical applications of hands-free communication.

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.

In last 10 years, several noise reduction (NR) algorithms have been proposed to be combined with the blind source separation techniques to separate speech and noise signals from blind noisy observations. More often, techniques use voice activity detector (VAD) systems for the optimal solution. In this paper, we propose a new backward blind source separation (BBSS) structure that uses the input correlation properties to provide: (i) high convergence rates and good tracking capabilities, since the acoustic environments imply long and time-variant noise paths, and (ii) low misalignment and robustness against different noise type variations and double-talk. The proposed algorithm has an automatic behavior to enhance noisy speech signals, and do not need any VAD systems to separate speech and noise signals. The obtained results in terms of several objective criteria show the good performance properties of the proposed algorithm in comparison with state-of-the-art algorithms.

<p indent="0mm">Based on the speech data in Mongolian, Tibetan, and Uyghur speech data from Chinese minority regions in 2015, we adopted a double threshold Voice Activity Detection method with short-time energy and short-time zero-crossing rate to obtain multiple voice fragments of each sentence speech. The result dataset contains 1657 Mongolian speech fragments, 666 Tibetan speech fragments and 756 Uygur speech fragments. The total volume of the data is about 111 MB. Through automatic software segmentation and multiple auditing and proofreading by language experts, we have obtained high-quality voice fragment data of Mongolian, Tibetan and Uygur, which can be applied to minority speech recognition, voice activity detection, speech enhancement, speech synthesis and language teaching.

Voice activity detection (VAD) in noisy environments is a very important preprocessing scheme in speech communication technology, a field which includes speech recognition, speech coding, speech enhancement and captioning video contents. We have developed a VAD method for noisy environments based on the modulation spectrum. In Experiment 1, we investigate the optimal ranges of speech and modulation frequencies for the proposed algorithm by using the simulated data in the CENSREC-1-C corpus. Results show that when we combine an upper limit frequency between 1,000 and 2,000 Hz with a lower limit frequency of less than 300 Hz as speech frequency bands, error rates are lower than with other bands. Furthermore, when we use the frequency components of the modulation spectrum between 3–9, 3–11, 3–14, 3–18, 4–9, 4–11, 4–14, 4–18, 5–7, 5–9, 5–11, or 5–14 Hz, the proposed method performs VAD well. In Experiment 2, we use one of the best parameter settings from Experiment 1 and evaluate the real environment data in the CENSREC-1-C corpus by comparing our method with other conventional methods. Improvements were observed from the VAD results for each SNR condition and noise type.

This paper proposes robust feature extraction for accurate voice activity detection (VAD). VAD is one of the principal modules for speech signal processing such as speech codec, speech enhancement, and speech recognition. Noisy environments contain nonstationary noises causing the accuracy of the VAD to drastically decline because the fluctuation of features in the noise intervals results in increased false alarm rates. In this paper, in order to improve the VAD performance, harmonic-weighted energy is proposed. This feature extraction method focuses on voiced speech intervals and weighted harmonic-to-noise ratios to determine the amount of the harmonicity to frame energy. For performance evaluation, the receiver operating characteristic curves and equal error rate are measured.

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.