Publication Details

From Simulated Mixtures to Simulated Conversations as Training Data for End-to-End Neural Diarization

LANDINI Federico Nicolás, LOZANO Díez Alicia, DIEZ Sánchez Mireia and BURGET Lukáš. From Simulated Mixtures to Simulated Conversations as Training Data for End-to-End Neural Diarization. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. Incheon: International Speech Communication Association, 2022, pp. 5095-5099. ISSN 1990-9772. Available from: https://www.isca-speech.org/archive/pdfs/interspeech_2022/landini22_interspeech.pdf
Czech title
Od simulovaných směsí k simulovaným konverzacím využitým jako trénovací data pro end-to-end neurální diarizaci
Type
conference paper
Language
english
Authors
Landini Federico Nicolás (DCGM FIT BUT)
Lozano Díez Alicia (UAM)
Diez Sánchez Mireia, M.Sc., Ph.D. (DCGM FIT BUT)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
URL
Keywords

peaker diarization, end-to-end neural diariza- tion, simulated conversations

Abstract

End-to-end neural diarization (EEND) is nowadays one of the most prominent research topics in speaker diarization. EEND presents an attractive alternative to standard cascaded diarization systems since a single system is trained at once to deal with the whole diarization problem. Several EEND variants and approaches are being proposed, however, all these models require large amounts of annotated data for training but available annotated data are scarce. Thus, EEND works have used mostly simulated mixtures for training. However, simulated mixtures do not resemble real conversations in many aspects. In this work we present an alternative method for creating synthetic conversations that resemble real ones by using statistics about distributions of pauses and overlaps estimated on genuine conversations. Furthermore, we analyze the effect of the source of the statistics, different augmentations and amounts of data. We demonstrate that our approach performs substantially better than the original one, while reducing the dependence on the fine-tuning stage. Experiments are carried out on 2-speaker telephone conversations of Callhome and DIHARD 3. Together with this publication, we release our implementations of EEND and the method for creating simulated conversations.

Published
2022
Pages
5095-5099
Journal
Proceedings of Interspeech - on-line, vol. 2022, no. 9, ISSN 1990-9772
Proceedings
Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Conference
Interspeech Conference, Incheon, KR
Publisher
International Speech Communication Association
Place
Incheon, KR
DOI
UT WoS
000900724505055
EID Scopus
BibTeX
@INPROCEEDINGS{FITPUB12846,
   author = "Nicol\'{a}s Federico Landini and Alicia D\'{i}ez Lozano and Mireia S\'{a}nchez Diez and Luk\'{a}\v{s} Burget",
   title = "From Simulated Mixtures to Simulated Conversations as Training Data for End-to-End Neural Diarization",
   pages = "5095--5099",
   booktitle = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
   journal = "Proceedings of Interspeech - on-line",
   volume = 2022,
   number = 9,
   year = 2022,
   location = "Incheon, KR",
   publisher = "International Speech Communication Association",
   ISSN = "1990-9772",
   doi = "10.21437/Interspeech.2022-10451",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/12846"
}
Back to top