Detail publikačního výsledku

Training Speaker Embedding Extractors Using Multi-Speaker Audio with Unknown Speaker Boundaries

STAFYLAKIS, T.; MOŠNER, L.; PLCHOT, O.; ROHDIN, J.; SILNOVA, A.; BURGET, L.; ČERNOCKÝ, J.

Originální název

Training Speaker Embedding Extractors Using Multi-Speaker Audio with Unknown Speaker Boundaries

Anglický název

Training Speaker Embedding Extractors Using Multi-Speaker Audio with Unknown Speaker Boundaries

Druh

Stať ve sborníku v databázi WoS či Scopus

Originální abstrakt

In this paper, we demonstrate a method for training speaker em- bedding extractors using weak annotation. More specifically, we are using the full VoxCeleb recordings and the name of the celebrities appearing on each video without knowledge of the time intervals the celebrities appear in the video. We show that by combining a baseline speaker diarization algorithm that re- quires no training or parameter tuning, a modified loss with aggregation over segments, and a two-stage training approach, we are able to train a competitive ResNet-based embedding extractor. Finally, we experiment with two different aggregation functions and analyze their behaviour in terms of their gradients.

Anglický abstrakt

In this paper, we demonstrate a method for training speaker em- bedding extractors using weak annotation. More specifically, we are using the full VoxCeleb recordings and the name of the celebrities appearing on each video without knowledge of the time intervals the celebrities appear in the video. We show that by combining a baseline speaker diarization algorithm that re- quires no training or parameter tuning, a modified loss with aggregation over segments, and a two-stage training approach, we are able to train a competitive ResNet-based embedding extractor. Finally, we experiment with two different aggregation functions and analyze their behaviour in terms of their gradients.

Klíčová slova

Speaker Embedding Extractors, Multi-Speaker Audio, Unknown Speaker Boundaries

Klíčová slova v angličtině

Speaker Embedding Extractors, Multi-Speaker Audio, Unknown Speaker Boundaries

Autoři

STAFYLAKIS, T.; MOŠNER, L.; PLCHOT, O.; ROHDIN, J.; SILNOVA, A.; BURGET, L.; ČERNOCKÝ, J.

Rok RIV

2023

Vydáno

18.09.2022

Nakladatel

International Speech Communication Association

Místo

Incheon

Kniha

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

ISSN

1990-9772

Periodikum

Proceedings of Interspeech

Svazek

2022

Číslo

9

Stát

Francouzská republika

Strany od

605

Strany do

609

Strany počet

5

URL

https://www.isca-speech.org/archive/pdfs/interspeech_2022/stafylakis22_interspeech.pdf

Plný text v Digitální knihovně

http://hdl.handle.net/

BibTex

@inproceedings{BUT179781,
  author="Themos {Stafylakis} and Ladislav {Mošner} and Oldřich {Plchot} and Johan Andréas {Rohdin} and Anna {Silnova} and Lukáš {Burget} and Jan {Černocký}",
  title="Training Speaker Embedding Extractors Using Multi-Speaker Audio with Unknown Speaker Boundaries",
  booktitle="Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
  year="2022",
  journal="Proceedings of Interspeech",
  volume="2022",
  number="9",
  pages="605--609",
  publisher="International Speech Communication Association",
  address="Incheon",
  doi="10.21437/Interspeech.2022-10165",
  issn="1990-9772",
  url="https://www.isca-speech.org/archive/pdfs/interspeech_2022/stafylakis22_interspeech.pdf"
}

Dokumenty

stafylakis_interspeech2022_training