Robust Voice Activity Detection Algorithm Research Articles

Robust voice activity detection using an auditory-inspired masked modulation encoder based convolutional attention network

Deep learning has revolutionized voice activity detection (VAD) by offering promising solutions. However, directly applying traditional features, such as raw waveforms and Mel-frequency cepstral coefficients, to deep neural networks often leads to degraded VAD performance due to noise interference. In contrast, humans possess the remarkable ability to discern speech in complex and noisy environments, which motivated us to draw inspiration from the human auditory system. We propose a robust VAD algorithm called auditory-inspired masked modulation encoder based convolutional attention network (AMME-CANet) that integrates our AMME with CANet. Firstly, we investigate the design of auditory-inspired modulation features as a deep-learning encoder (AME), effectively simulating the process of sound-signal transmission to inner ear hair cells and subsequent modulation filtering by neural cells. Secondly, building upon the observed masking effects in the human auditory system, we enhance our auditory-inspired modulation encoder by incorporating a masking mechanism resulting in the AMME. The AMME amplifies cleaner speech frequencies while suppressing noise components. Thirdly, inspired by the human auditory mechanism and capitalizing on contextual information, we leverage the attention mechanism for VAD. This methodology uses an attention mechanism to assign higher weights to contextual information containing richer and more informative cues. Through extensive experimentation and evaluation, we demonstrated the superior performance of AMME-CANet in enhancing VAD under challenging noise conditions.

Voice Activity Detection Using Generalized Exponential Kernels for Time and Frequency Domains

In this paper, we present a simple and robust voice activity detection algorithm using a generalized exponential kernel (GEVAD). Taking advantage of a non-linear metrics, kernel functions are used to classify acoustic signatures as speech and non-speech. The analysis are performed for different signal features in the frequency domain, based on elements of the short-time discrete Fourier transform as well as in time domain, namely the short time energy. The performance of all the features was compared to each other and the best was assessed by the GEVAD algorithm. Also, insights of how to choose the best kernel function are given based in frame error rate analysis. To test the efficiency of our approaches, comparisons with other existing algorithms are presented, with GEVAD showing better performance in adverse environments as stationary (and non-stationary) low signal-to-noise ratio.

Robust Voice Activity Detection Algorithm based on Long Term Dominant Frequency and Spectral Flatness Measure

Robust Voice Activity Detection Algorithm based on Long Term Dominant Frequency and Spectral Flatness Measure

Formant-Based Robust Voice Activity Detection

Voice activity detection (VAD) can be used to distinguish human speech from other sounds, and various applications can benefit from VAD-including speech coding and speech recognition. To accurately detect voice activity, the algorithm must take into account the characteristic features of human speech and/or background noise. In many real-life applications, noise frequently occurs in an unexpected manner, and in such situations, it is difficult to determine the characteristics of noise with sufficient accuracy. As a result, robust VAD algorithms that depend less on making correct noise estimates are desirable for real-life applications. Formants are the major spectral peaks of the human voice, and these are highly useful to distinguish vowel sounds. The characteristics of the spectral peaks are such that, these peaks are likely to survive in a signal after severe corruption by noise, and so formants are attractive features for voice activity detection under low signal-to-noise ratio (SNR) conditions. However, it is difficult to accurately extract formants from noisy signals when background noise introduces unrelated spectral peaks. Therefore, this paper proposes a simple formant-based VAD algorithm to overcome the problem of detecting formants under conditions with severe noise. The proposed method achieves a much faster processing time and outperforms standard VAD algorithms under various noise conditions. The proposed method is robust against various types of noise and produces a light computational load, so it is suitable for use in various applications.

Robust Voice Activity Detection Based on Concept of Modulation Transfer Function in Noisy Reverberant Environments

Most of the current voice activity detection (VAD) algorithms deal with clean (noiseless) speech or speech with additive noise conditions. They cannot work in noisy reverberant environments or work poorly if they do, because speech is smeared due to the effects of noise and reverberation. This paper proposes a robust VAD algorithm for precisely detecting speech and non-speech periods in noisy reverberant environments. The proposed VAD algorithm consists of three blocks. The first block is an estimation of the signal to noise ratio (SNR) which is used to mitigate the additive noise effect on the speech power envelope. The second block is a speech power envelope dereverberation based on the modulation transfer function concept. The last block is a threshold processing on the dereverberated speech power envelope for speech/non-speech decision. Experiments on VAD in both artificial and realistic noisy reverberant environments revealed that the proposed VAD algorithm significantly outperforms the conventional VAD algorithms.

Robust Voice Activity Detection Algorithm Based on Feature of Frequency Modulation of Harmonics and Its DSP Implementation

Robust Voice Activity Detection Algorithm Based on Feature of Frequency Modulation of Harmonics and Its DSP Implementation

A unified approach to speech enhancement and voice activity detection

In this paper, a unified system for voice activity detection (VAD) and speech enhancement is proposed. In the proposed system, there is mutual exchange of information between VAD and speech enhancement blocks. A new and robust VAD algorithm is implemented for the VAD block of the unified system. The newly proposed VAD algorithm uses a periodicity measure and an energy measure obtained from spectral energy distribution and spectral energy difference of the input speech data. For the speech enhancement block, the modified Wiener filtering (MWF) approach is utilized. It has been shown that the utilization of information exchange between the VAD and MWF algorithms in the unified system increases the performance of both algorithms and the proposed unified system improves the robustness of a speech recognition system significantly. Both of the enhanced algorithms are noniterative. Therefore, the proposed unified system is computationally attractive for real-time applications.

Robust voice activity detection based on harmonic to noise ratio

A robust voice activity detection algorithm based on harmonic to noise ratio (HNR) is proposed. Harmonic to noise ratio is high in voice segments, because most of the voice energy distributes on the harmonic structure. However, it is unreliable or complicated to estimate the harmonic frequencies of noisy speech, and the HNR in full frequency band is not robust for environments with non-stationary band-limited noise. In this paper, several harmonic templates with fundamental frequency changing in log-scale step are used to match the wide-band voice harmonic structure, and the fundamental frequencies are not need to be estimated. To avoid the non-stationary band-limited noise, the contaminated frequencies are neglected automatically by frequency bin selection, which discards the harmonic and the noisy bins with the highest and lowest energy to keep the main clear harmonic structure. The final voice activity detection is based on the HNR of continuous frames, and it shows robust performance on several databases.

A Robust, Real-Time Voice Activity Detection Algorithm for Embedded Mobile Devices

When an Automatic Speech Recognition (ASR) system is applied in noisy environments, Voice Activity Detection (VAD) is crucial to the performance of the overall system. The employment of the VAD for ASR on embedded mobile systems will minimize physical distractions and make the system convenient to use. Conventional VAD algorithm is of high complexity, which makes it unsuitable for embedded mobile devices; or of low robustness, which holds back its application in mobile noisy environments. In this paper, we propose a robust VAD algorithm specifically designed for ASR on embedded mobile devices. The architecture of the proposed algorithm is based on a two-level decision making strategy, where there is an interaction between a lower features-based level and subsequent decision logic based on a finite-state machine. Many discriminating features are employed in the lower level to improve the robustness of the VAD. The two-level decision strategy allows different features to be used in different states and reduces the cost of the algorithm, which makes the proposed algorithm suitable for embedded mobile devices. The evaluation experiments show the proposed VAD algorithm is robust and contribute to the overall performance gain of the ASR system in various acoustic environments.

Robust voice activity detection algorithm for estimatingnoise spectrum

A new voice activity detection(VAD) algorithm is proposed for estimating the spectrum of car noise in which noise is filtered out in the frequency domain. The proposed algorithm uses the log energy parameters which are composed of two parts in the critical band. The algorithm detects the noise period by applying two adaptive thresholds to each part. Using the noise period we can reliably estimate the time-varying noise characteristics. The advantage of the proposed technique is that it can prevent incorrect detections caused by unvoiced or nasal sounds with high frequency components being covered by car noise with low frequency components. The algorithm is suitable for real time implementation with one microphone. Also, a speaker-independent speech recognition system has been implemented for car navigation using a fixed point Oak DSP system, which incorporates the proposed VAD algorithm. The system enhanced the recognition rates for 12 isolated command words to 94.52% compared with the 80.7% of the baseline recogniser.

A Robust, Real-Time Voice Activity Detection Algorithm for Embedded Mobile Devices

When an Automatic Speech Recognition (ASR) system is applied in noisy environments, Voice Activity Detection (VAD) is crucial to the performance of the overall system. The employment of the VAD for ASR on embedded mobile systems will minimize physical distractions and make the system convenient to use. Conventional VAD algorithm is of high complexity, which makes it unsuitable for embedded mobile devices; or of low robustness, which holds back its application in mobile noisy environments. In this paper, we propose a robust VAD algorithm specifically designed for ASR on embedded mobile devices. The architecture of the proposed algorithm is based on a two-level decision making strategy, where there is an interaction between a lower features-based level and subsequent decision logic based on a finite-state machine. Many discriminating features are employed in the lower level to improve the robustness of the VAD. The two-level decision strategy allows different features to be used in different states and reduces the cost of the algorithm, which makes the proposed algorithm suitable for embedded mobile devices. The evaluation experiments show the proposed VAD algorithm is robust and contribute to the overall performance gain of the ASR system in various acoustic environments.