A Triplet Ranking-Based Neural Network for Speaker Diarization and Linking

@inproceedings{Lan2017ATR,
  title={A Triplet Ranking-Based Neural Network for Speaker Diarization and Linking},
  author={Ga{\"e}l Le Lan and Delphine Charlet and Anthony Larcher and Sylvain Meignier},
  booktitle={INTERSPEECH},
  year={2017}
}
This paper investigates a novel neural scoring method, based on conventional i-vectors, to perform speaker diarization and linking of large collections of recordings. Using triplet loss for training, the network projects i-vectors in a space that better separates speakers in terms of cosine similarity. Experiments are run on two French TV collections built from REPERE [1] and ETAPE [2] campaigns corpora, the system being trained on French Radio data. Results indicate that the proposed approach… CONTINUE READING

From This Paper

Figures, tables, results, and topics from this paper.

Key Quantitative Results

  • Results indicate that the proposed approach outperforms conventional cosine and Probabilistic Linear Discriminant Analysis scoring methods on both withinand cross-recording diarization tasks, with a Diarization Error Rate reduction of 14% in average.

References

Publications referenced by this paper.
Showing 1-10 of 27 references

FaceNet: A unified embedding for face recognition and clustering

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2015
View 4 Excerpts
Highly Influenced

Front-End Factor Analysis For Speaker Verification

2018 International Conference on Communications (COMM) • 2018
View 2 Excerpts

Keras

F. Chollet
https://github.com/fchollet/keras, 2017. 3576 • 2017
View 2 Excerpts

TristouNet: Triplet loss for speaker turn embedding

2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2017
View 3 Excerpts

An extensible speaker identification sidekit in Python

2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2016
View 1 Excerpt

Speaker Diarization and Linking of Meeting Data

IEEE/ACM Transactions on Audio, Speech, and Language Processing • 2016
View 1 Excerpt

Speaker diarization with unsupervised training framework

2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2016
View 1 Excerpt

A cluster-voting approach for speaker diarization and linking of Australian broadcast news recordings

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2015
View 1 Excerpt

Similar Papers

Loading similar papers…