Speaker-and-environment change detection in broadcast news using the common component GMM-based divergence measure
نویسندگان
چکیده
In this paper, a GMM with common mixture components, referred to as the common component GMM (CCGMM), is proposed to be the signal model for calculating the diversity measure for the speaker-and-environment change detection in broadcast news signal. The use of GMM is to increase the accuracy of audio signal modeling while the use of common mixture components is to solve the complexity problem of parameter estimation and similarity measure evaluation. Experimental results on a TV broadcast news database showed that it outperformed a BIC-based method. A MDR of 21.9% with 16.0% FAR was achieved.
منابع مشابه
Speaker-and-Environment Change Detection in Broadcast News Using Maximum Divergence Common Component GMM
In this paper, the supervised maximum-divergence common component GMM (MD-CCGMM) model was used to the speaker-andenvironment change detection in broadcast news signal. In order to discriminate the speaker-and-environment change in broadcast news, the MD-CCGMM signal model will maximize the likelihood of CCGMM signal modeling and the divergence measure of different audio signal segments simulta...
متن کاملOn-line incremental speaker adaptation with automatic speaker change detection
In order to improve the performance of speech recognition systems when speakers change frequently and each of them utters a series of several sentences, a new unsupervised, online and incremental speaker adaptation technique combined with automatic detection of speaker changes is proposed. The speaker change is detected by comparing likelihoods using speaker-independent and speaker-adaptive GMM...
متن کاملUniversal Background Models for Real-time Speaker Change Detection
This paper addresses the problem of real-time speaker change detection in TV news broadcast, in which no prior knowledge on speakers is assumed. To remove the unreliable frames and background frames in the speech stream, we propose a new approach for feature categorization based on Gaussian Mixture Model Universal Background Model (GMM-UBM). The feature vectors are categorized into three sets, ...
متن کاملA System for Speaker Detection and Tracking in Audio Broadcast News
A system for speaker-based audio-indexing and an application for speaker-tracking in broadcast news audio are presented. The process of producing an indexing information in continuous audio streams based on detected speakers is composed of several tasks and is therefore treated as a multistage process. The main building blocks of such an indexing system include components for an audio segmentat...
متن کاملUsing acoustic condition clustering to improve acoustic change detection on broadcast news
We have developed a system that breaks input speech into segments using an acoustic similarity measure. The aim is to detect the time points where the acoustic characteristics change, usually due to speaker changes but also resulting from changes in the acoustic environment. We have also developed a system to cluster the segments generated by the first system into clusters composed of homogeneo...
متن کامل