• Computer Science
  • Published in INTERSPEECH 2006

Friends and enemies: a novel initialization for speaker diarization

@inproceedings{Mir2006FriendsAE,
  title={Friends and enemies: a novel initialization for speaker diarization},
  author={Xavier Anguera Mir{\'o} and Chuck Wooters and Javier Hernando},
  booktitle={INTERSPEECH},
  year={2006}
}
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 performance and robustness. In this paper we present a novel approach that obtains a desired initial number… CONTINUE READING

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 17 CITATIONS

New insights into hierarchical clustering and linguistic normalization for speaker diarization

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Machine learning for gesture recognition from videos

VIEW 1 EXCERPT
CITES BACKGROUND

Speaker Diarization: A Review of Recent Research

VIEW 1 EXCERPT
CITES BACKGROUND

Fast speaker diarization based on binary keys

VIEW 1 EXCERPT
CITES BACKGROUND

A Comparable Study on PNCC in Speaker Diarization for Meetings

  • Qiao Li, Qing Fan, Yunpeng Xiao, Weiping Ye
  • Computer Science
  • 2010 First ACIS International Symposium on Cryptography, and Network Security, Data Mining and Knowledge Discovery, E-Commerce and Its Applications, and Embedded Systems
  • 2010
VIEW 1 EXCERPT
CITES BACKGROUND

An adaptive initialization method for speaker Diarization based on prosodic features

VIEW 1 EXCERPT
CITES METHODS

Using audio and visual cues for speaker diarisation initialisation

VIEW 2 EXCERPTS
CITES BACKGROUND

Speaker clustering performance improvement using eigen-voice speaker adaptation

VIEW 1 EXCERPT
CITES METHODS

References

Publications referenced by this paper.
SHOWING 1-10 OF 11 REFERENCES

Nuts and Flakes: a Study of Data Characteristics in Speaker Diarization

Approaches and applications of audio diarization

Robust speaker change detection

A robust speaker clustering algorithm

  • Jitendra Ajmera, Chuck Wooters
  • Computer Science
  • 2003 IEEE Workshop on Automatic Speech Recognition and Understanding (IEEE Cat. No.03EX721)
  • 2003

Clustering via the Bayesian information criterion with applications in speech recognition