Detail publikačního výsledku

Analysis of the ABC classification backends for NIST SRE24

CUMANI, S.; SILNOVA, A.; BARAHONA, S.; MOŠNER, L.; PLCHOT, O.; ROHDIN, J.

Originální název

Analysis of the ABC classification backends for NIST SRE24

Anglický název

Analysis of the ABC classification backends for NIST SRE24

Druh

Stať ve sborníku v databázi WoS či Scopus

Originální abstrakt

We present an analysis of the classification backends of the ABC submission for the audio tracks of the NIST 2024 Speaker Recognition Evaluation (SRE24). Our analysis covers embedding pre-processing, classification and score-level normalization, calibration and fusion strategies adopted to cope with the source, language and duration mismatch challenges of SRE24. We show that Pairwise Support Vector Machines provide the best results, which can be further improved, for single frontends, through score-level fusion of additional classifiers. We also show that condition-aware score calibration can mitigate the effects of source mismatch, whereas score normalization methods proved ineffective. Finally, we show that generative calibration is able to achieve competitive results with respect to other approaches.

Anglický abstrakt

We present an analysis of the classification backends of the ABC submission for the audio tracks of the NIST 2024 Speaker Recognition Evaluation (SRE24). Our analysis covers embedding pre-processing, classification and score-level normalization, calibration and fusion strategies adopted to cope with the source, language and duration mismatch challenges of SRE24. We show that Pairwise Support Vector Machines provide the best results, which can be further improved, for single frontends, through score-level fusion of additional classifiers. We also show that condition-aware score calibration can mitigate the effects of source mismatch, whereas score normalization methods proved ineffective. Finally, we show that generative calibration is able to achieve competitive results with respect to other approaches.

Klíčová slova

Classification backend | Pairwise Support Vector Machine | Score calibration | Speaker Recognition Evaluation | Speaker verification

Klíčová slova v angličtině

Classification backend | Pairwise Support Vector Machine | Score calibration | Speaker Recognition Evaluation | Speaker verification

Autoři

CUMANI, S.; SILNOVA, A.; BARAHONA, S.; MOŠNER, L.; PLCHOT, O.; ROHDIN, J.

Rok RIV

2026

Vydáno

17.08.2025

Nakladatel

International Speech Communication Association

Místo

Rotterdam

Kniha

Proceedings of the Annual Conference of the International Speech Communication Association Interspeech

Periodikum

Interspeech

Stát

Nizozemsko

Strany od

3978

Strany do

3982

Strany počet

5

URL

https://www.isca-archive.org/interspeech_2025/cumani25_interspeech.pdf

BibTex

@inproceedings{BUT199933,
  author="{} and Anna {Silnova} and  {} and Ladislav {Mošner} and Oldřich {Plchot} and Johan Andréas {Rohdin}",
  title="Analysis of the ABC classification backends for NIST SRE24",
  booktitle="Proceedings of the Annual Conference of the International Speech Communication Association Interspeech",
  year="2025",
  journal="Interspeech",
  pages="3978--3982",
  publisher="International Speech Communication Association",
  address="Rotterdam",
  doi="10.21437/Interspeech.2025-146",
  url="https://www.isca-archive.org/interspeech_2025/cumani25_interspeech.pdf"
}

Dokumenty

cumani_2025_interspeech