Discrimination of speech from nonspeeech in broadcast news based on modulation frequency features

Abstract

In audio content analysis, the discrimination of speech and non-speech is the first processing step before speaker segmentation and recognition, or speech transcription. Speech/non-speech segmentation algorithms usually consist of a frame based scoring phase using MFCC features, combined with a smoothing phase. In this paper, a content based speech discrimination algorithm is designed to exploit long-term information inherent in modulation spectrum. In order to address the varying degrees of redundancy and discriminative power of the acoustic and modulation frequency subspaces, we first employ a generalization of SVD to tensors (Higher Order SVD) to reduce dimensions. Projection of modulation spectral features on the principal axes with the higher energy in each subspace results in a compact set of features with minimum redundancy. We further estimate the relevance of these projections to speech discrimination based on mutual information to the target class. This system is built upon a segment based SVM classifier in order to recognize the presence of voice activity in audio signal. Detection experiments using Greek and U.S. English broadcast news data composed of many speakers in various acoustic conditions suggest that the system provides complementary information to state-of-the-art melcepstral features.

A New Truncation Strategy for the Higher-Order Singular Value Decomposition

“…The HOSVD has been applied in numerous application domains [29], such as image processing [9,32,39,61], pattern recognition [49,50,59,60,62], data mining and machine learning [33,34,52,53], signal processing [12,19,36,37,38,45], psychometrics [54,55,56], chemometrics [5], and biomedicine [16,40,41]. Aside from its use in applications, the HOSVD is also of considerable theoretical importance.…”

Albayzín-2014 evaluation: audio segmentation and classification in broadcast news domains

“…These characteristics are referred in the literature as segment-based features [29,30]. For example, in [31], a content-based speech discrimination algorithm is designed to exploit the long-term information inherent in the modulation spectrum; and in [32], authors propose two segment-based features: the variance of the spectrum flux (VSF) and the variance of the zero crossing rate (VZCR).…”

Data-Driven Audio Feature Space Clustering for Automatic Sound Recognition in Radio Broadcast News

“…Some of the widely used are: (i) multi-class problem, 10 (ii) binary-classes problem, 37 (iii) hierarchical structure of the classes problem, 11 (iv) two-groups or multi-group of classes problem 28 and (v) detection of a class over the other classes problem. 19,48 In this work, we present a broadcast news sound recognition methodology based on widely known and used audio features. The implemented framework clusters the audio feature space to subspaces, based on data-driven criteria.…”