Boosting Contextual Information for Deep Neural Network Based Voice Activity Detection

• Published in: IEEE/ACM transactions on audio, speech, and language processing Vol. 24; no. 2; pp. 252 - 264
• Main Authors: Zhang, Xiao-Lei, Wang, DeLiang
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.02.2016; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Acoustics; Audio signals; Classifiers; Cochleagram; deep neural network; ensemble learning; Frames; multi-resolution stacking; Neural networks; Noise; noise-independent training; Signal processing; Signal to noise ratio; Speech; Stacking; Training; Voice; voice activity detection
• ISSN: 2329-9290; 2329-9304
• DOI: 10.1109/TASLP.2015.2505415

Voice activity detection (VAD) is an important topic in audio signal processing. Contextual information is important for improving the performance of VAD at low signal-to-noise ratios. Here we explore contextual information by machine learning methods at three levels. At the top level, we employ an ensemble learning framework, named multi-resolution stacking (MRS), which is a stack of ensemble classifiers. Each classifier in a building block inputs the concatenation of the predictions of its lower building blocks and the expansion of the raw acoustic feature by a given window (called a resolution). At the middle level, we describe a base classifier in MRS, named boosted deep neural network (bDNN). bDNN first generates multiple base predictions from different contexts of a single frame by only one DNN and then aggregates the base predictions for a better prediction of the frame, and it is different from computationally-expensive boosting methods that train ensembles of classifiers for multiple base predictions. At the bottom level, we employ the multi-resolution cochleagram feature, which incorporates the contextual information by concatenating the cochleagram features at multiple spectrotemporal resolutions. Experimental results show that the MRS-based VAD outperforms other VADs by a considerable margin. Moreover, when trained on a large amount of noise types and a wide range of signal-to-noise ratios, the MRS-based VAD demonstrates surprisingly good generalization performance on unseen test scenarios, approaching the performance with noise-dependent training.