Clustering initialization based on spatial information for speaker diarization of meetings

نویسندگان

  • Jordi Luque
  • Carlos Segura
  • Javier Hernando
چکیده

This paper proposes an initialization for an agglomerative system applied to speaker diarization in the meeting environment. The initialization is based on a previous clustering of the temporal sequence generated by the estimation of the Time Delay of Arrival (TDOA) among pair of sensors. That initial clustering has the purpose of obtaining initial classes with speaker information from a sole speaker. The aim is to ensure the purity of the initial segments based on the position of the speakers in a meeting along time. The TDOA initialization was tested with the dataset used in the RT07s evaluation where an improvement of the diariazation error rate is obtained with respect to the classical uniform initialization. The most of the experiments show that the purity of the beginning segments leads to a better clustering on the posterior hierarchical strategy based on cepstral features.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Information Bottleneck Features for HMM/GMM Speaker Diarization of Meetings Recordings

Improved diarization results can be obtained through combination of multiple systems. Several combination techniques have been proposed based on output voting, initialization and also integrated approaches. This paper proposes and investigates a novel approach to combine diarization systems through the use of features. A first diarization system, based on the Information Bottleneck, is used to ...

متن کامل

Robust Speaker Diarization for Meetings: ICSI RT06S Meetings Evaluation System

In this paper we present the ICSI speaker diarization system submitted for the NIST Rich Transcription evaluation (RT06s) [1] conducted on the meetings environment. The presented system is based on the RT05s system, which uses agglomerative clustering with a modified Bayesian Information Criterion (BIC) measure to decide which pairs of clusters to merge and to determine when to stop merging clu...

متن کامل

Friends and enemies: a novel initialization for speaker diarization

The task of speaker diarization consists of answering the question “Who spoke when?”. The most commonly used approach to speaker diarization is agglomerative clustering of multiple initial clusters. Even though the initial clustering is greatly modified by iterative cluster merging and possibly multiple resegmentations of the data, the initialization algorithm is a key module for system perform...

متن کامل

Multi-stage Speaker Diarization for Conference and Lecture Meetings

The LIMSI RT-07S speaker diarization system for the conference and lecture meetings is presented in this paper. This system builds upon the RT06S diarization system designed for lecture data. The baseline system combines agglomerative clustering based on Bayesian information criterion (BIC) with a second clustering using state-of-the-art speaker identification (SID) techniques. Since the baseli...

متن کامل

Speaker Diarization in Meetings Domain

The purpose of this study is to develop robust techniques for speaker segmentation and clustering with focus on meetings domain. The techniques examined can however be applied to any other domains such as telephone and broadcast news. Traditional techniques for speaker diarization developed for telephone conversations or broadcast news are based on a single channel, which is notably different f...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2008