Voice activity detection (VAD) has several applications in different areas of speech processing, as such speech recognition, speech compression and noise reduction. In this paper first, the related approaches presented in the literatures will be investigated. Next, a new procedure is proposed for distinguishing between silence and non-silence regions of a speech signal. The proposed technique is based on wavelet transform, because it provides a high capability of energy-separation in different sub bands. The obtained results confirm that the proposed method shows significant improvements in compare with other methods.

Speech constitutes much of the communicated information; most other perceived audio signals do not carry nearly as much information. Indeed, much of the non-speech signals maybe classified as ‘noise’ in human communication. The process of separating conversational speech and noise is termed voice activity detection (VAD). This paper describes a new approach to VAD which is based on the Wavelet Packet Transform (WPT). Our algorithm utilizes the differences between spectral distribution of human speech (voice) and general noise. First, the algorithm performs wavelet transform on the signal resulting in its decomposition into subbands using coefficients of WPT, and then it detects the voice within the signal by comparing the subband energy of components between detail and approximation coefficients. Computer simulation results are given to illustrate the effectiveness of our new VAD algorithms.

In Persian, like many other languages, there are three voices, passive, active and middle. In Persian, middle voice, like passive voice, is a structure consisting of a one-place predicate. Middle verbs are morphologically active and semantically passive. The purpose of this article is to describe the properties of middle construction in Persian and to explore the derivation of middle as a transitive structure within the framework of the latest version of Generative Grammar.

Background and Aim: Autism spectrum is a neurological disorder that manifests itself in the early years of a child's development. People with autism face challenges in regulating emotions and express their emotional states in different ways. The current research presents a vocal activity detection (VAD) system adapted to the voices of autistic children. Methods: The proposed VAD system is a Recurrent Neural Network (RNN) with short-term memory (LSTM) cells. The data includes 25 English-speaking autistic children performing a structured learning activity and was collected as part of the DE-ENIGMA project. Results: Our experiments show that the pediatric VAD system performs less well than our generic VAD system trained under the same conditions, as we obtain system performance characteristic curve under the curve (ROC-AUC) criteria of 0. 662 and 0. 850, respectively. The SER results show different performances between capacity and excitation, depending on the VAD system used, with a maximum match correlation coefficient (CCC) of 0. 263 and a minimum root mean square error (RMSE) of 0. 107. Conclusion: Although the performance of SER models is generally low, the pediatric VAD system can lead to slightly improved results compared to other VAD systems and especially the VAD-less baseline, which supports the hypothesized importance of pediatric VAD systems in the context under discussion.

This paper presents a set of voice activity detection (VAD) methods, that are easy to implement, robust against noise, and appropriate for real-time applications. The common characteristic is the use of a voting paradigm in all the proposed methods. In these methods, the decision on the voice activity of a given frame is based on comparing the features obtained from that frame with some thresholds. In the first method, a set of three features, namely frame energy, spectral flatness, and the most dominant frequency component is applied. In the second approach however, the spectral pattern of the frames of vowel sounds is used. To use the strengths of each of the above methods, the combination of these two decision approaches is also put forth in this paper. The performance of the proposed approaches is evaluated on different speech datasets with different noise characteristics and SNR levels. The approaches are compared with some conventional VAD algorithm such as ITU G.729, AMR and AFE from different points of view. The evaluations show considerable performance improvement of the proposed approaches.