Voice activity detection using harmonic frequency components in likelihood ratio test

Abstract

This paper proposes a new statistical model-based likelihood ratio test (LRT) VAD to obtain reliable speech / non-speech decisions. In the proposed method, the likelihood ratio (LR) is calculated differently for voiced frames, as opposed to unvoiced frames: only DFT bins containing harmonic spectral peaks are selected for LR computation. To evaluate the new VAD's effectiveness in improving the noiserobustness of ASR, its decisions are applied to preprocessing techniques such as non-linear spectral subtraction, minimum mean square error short-time spectral amplitude estimator, and frame dropping. From the ASR experiments conducted on the Aurora2 database, the proposed harmonic frequency-based LRTs give better results than conventional LRT-based VADs and the standard G.729B and ETSI AMR VADs.

Voice/non-voice detection using phase of zero frequency filtered speech signal

“…Spectral domain VNV detection methods exploit the spectral harmonicity in voiced regions. Harmonic peaks in the amplitude spectrum of voiced speech regions are usually preserved in noisy speech ( Tan et al, 2010 ). Spectral harmonicity is exploited in developing the robust automatic speech recognition ( Beh & Ko, 2003 ) and speech enhancement ( Plapous et al, 2005 ) http://dx.doi.org/10.1016/j.specom.2016.01.008 0167-6393/© 2016 Elsevier B.V. All rights reserved.…”

Real-Time Robust Voice Activity Detection Using the Upper Envelope Weighted Entropy Measure and the Dual-Rate Adaptive Nonlinear Filter

“…Statistical models are superior to rule-based classification algorithms when the segments are not clearly demarcated. There are several popular statistical models in VAD systems such as the likelihood ratio test (LRT) [15]. Tan et al modified the LRT-based model by selecting discrete Fourier transform bins that consist of harmonic spectral peaks to determine the likelihood ratio.…”

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

“…Furthermore, it has been shown that the spectro-temporal analysis of the Fourier spectrogram can capture prominent acoustic "textures", such as pitch, harmonicity, formant, amplitude modulation (AM) and frequency modulation (FM) [34]. The pitch, harmonicity and formants are spectrum-related features have been considered in VAD algorithms [3], [21], [22]. The AM encodes the long-term variations of the envelope of the acoustic signal and was considered as in [15]- [18], [22].…”

“…Moreover, pitch (fundamental frequency) and harmonics of a voiced sound are perceptually important to human hearing [10], [19], [20]. This property leads to the approach of adopting harmonic-related features in VAD algorithms [3], [21], [22].…”