@inproceedings{82a68bd9e70a447b9782129b94e9abab,
title = "Speech Detection on Broadcast Audio",
abstract = "Speech boundary detection contributes to performance of speech based applications such as speech recognition and speaker recognition. Speech boundary detector implemented in this study works on broadcast audio as a pre-processor module of a keyword spotter. Speech boundary detection is handled in 3 steps. At first step, audio data is segmented into homogeneous regions in an unsupervised manner. After an ACTIVITY/NON-ACTIVITY decision is made for each region, ACTIVITY regions are classified as Speech/Non-speech via Gaussian Mixture Model (GMM) based classification. GMM's are trained using a novel feature, Spectral Flow Direction (SFD), and an improved multi-band harmonicity feature in addition to widely used Mel Frequency Cepstral Coefficients (MFCC's).",
keywords = "CLASSIFICATION, RETRIEVAL, MUSIC",
author = "Unal Zubari and Ozan, {Ezgi Can} and Acar, {Banu Oskay} and Tolga Ciloglu and Ersin Esen and Ates, {Tugrul K.} and Onur, {Duygu Oskay}",
year = "2010",
language = "English",
series = "European Signal Processing Conference",
publisher = "EUROPEAN ASSOC SIGNAL SPEECH & IMAGE PROCESSING-EURASIP",
pages = "85--89",
editor = "B Kleijn and J Larsen",
booktitle = "18TH European Signal Processing Conference (EUSIPCO-2010)",
note = "18th European Signal Processing Conference (EUSIPCO) ; Conference date: 23-08-2010 Through 27-08-2010",
}