A study of voice activity detection techniques for NIST speaker recognition evaluations

Abstract

Since 2008, interview-style speech has become an important part of the NIST Speaker Recognition Evaluations (SREs). Unlike telephone speech, interview speech has lower signal-to-noise ratio, which necessitates robust voice activity detectors (VADs). This paper highlights the characteristics of interview speech files in NIST SREs and discusses the difficulties in performing speech/non-speech segmentation in these files. To overcome these difficulties, this paper proposes using speech enhancement techniques as a preprocessing step for enhancing the reliability of energy-based and statisticalmodel-based VADs. A decision strategy is also proposed to overcome the undesirable effects caused by impulsive signals and sinusoidal background signals. The proposed VAD is compared with the ASR transcripts provided by NIST, VAD in the ETSI-AMR Option 2 coder, satistical-model (SM) based VAD, and Gaussian mixture model (GMM) based VAD. Experimental results based on the NIST 2010 SRE dataset suggest that the proposed VAD outperforms these conventional ones whenever interview-style speech is involved. This study also demonstrates that (1) noise reduction is vital for energy-based VAD under low SNR; (2) the ASR transcripts and ETSI-AMR speech coder do not produce accurate speech and non-speech segmentations; and (3) spectral subtraction makes better use of background spectra than the likelihood-ratio tests in the SM-based VAD. The segmentation files produced by the proposed VAD can be found in http://bioinfo.eie.polyu.edu.hk/ssvad.

Robust scream sound detection via sound event partitioning

“…1. A spectralsubtraction based voice activity detection (VAD) proposed in [24] is applied to detect the sound regions. MFCCs [6] and GFCCs [38][39][40] are extracted from the sound regions only.…”

The I4U Mega Fusion and Collaboration for NIST Speaker Recognition Evaluation 2016

“…Also, a vast majority of our sub-systems use energy-based voice activity detector (VAD) in view of its simplicity and effectiveness. Other options for VAD that have been adopted are (i) VQ-VAD [21] in Sys1 and Sys14, (ii) speech/non-speech probabilities inferred from the DNN senone posterior in Sys9, and (iii) two-channel VAD [22] [14,15,27], there are a handful of our sub-systems (six out of seventeen in Table 3) that have successfully incorporated deep learning in one form or another: (i) Deep bottleneck feature (DBF) in Sys9, (ii) Stacked bottleneck feature in Sys11, (iii) DNN posterior in Sys2, Sys9, Sys10, Sys16, (iv) Splice time delay DNN (TDNN) [16] in Sys2, and (v) Denoising autoencoder in Sys14. For the bottleneck features in Sys9 we used a DNN with seven hidden layers each having 1024 hidden units except for the third layer with only 80 units.…”

Finding Time Together: Detection and Classification of Focused Interaction in Egocentric Video

“…Voice Activity Detection (VAD) is widely researched in audio signal processing and used for audio conferencing, speech encoding, speech recognition, and speaker recognition [17,26]. VAD methods detect voice activity (primarily speech) from a noisy audio signal [16,24,29]. Video content-based camera motion analysis methods make use of template matching [1] and optical flow [6].…”