Výsledky vyhledávání

Multi-Speaker and Wide-Band Simulated Conversations as Training Data for End-to-End Neural Diarization

Autor: Federico Landini, Mireia Diez, Alicia Lozano-Diez, Lukáš Burget

End-to-end diarization presents an attractive alternative to standard cascaded diarization systems because a single system can handle all aspects of the task at once. Many flavors of end-to-end models have been proposed but all of them require (so fa

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f9909ef392675c87d49e66b250088a02
http://arxiv.org/abs/2211.06750

Zobrazit plný text záznamu

Analysis of Speaker Diarization Based on Bayesian HMM With Eigenvoice Priors

Autor: Jan Cernocky, Federico Landini, Mireia Diez, Lukas Burget

Publikováno v: IEEE/ACM Transactions on Audio, Speech, and Language Processing. 28:355-368

In our previous work, we introduced our Bayesian Hidden Markov Model with eigenvoice priors, which has been recently recognized as the state-of-the-art model for Speaker Diarization. In this article we present a more complete analysis of the Diarizat

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::a9d4b962a347760a3cfe2fbe701b2c82
https://doi.org/10.1109/taslp.2019.2955293

Zobrazit plný text záznamu

End-to-end DNN based text-independent speaker recognition for long and short utterances

Autor: Oldřich Plchot, Mireia Diez, Pavel Matějka, Anna Silnova, Ondřej Glembek, Lukas Burget, Johan Rohdin

Publikováno v: Computer Speech & Language. 59:22-35

Recently several end-to-end speaker verification systems based on deep neural networks (DNNs) have been proposed. These systems have been proven to be competitive for text-dependent tasks as well as for text-independent tasks with short utterances. H

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::e0f7e24c268055861f90bd3deec10c98
https://doi.org/10.1016/j.csl.2019.06.002

Zobrazit plný text záznamu

Bayesian HMM clustering of x-vector sequences (VBx) in speaker diarization: theory, implementation and analysis on standard tasks

Autor: Federico Landini, Mireia Diez, Lukas Burget, Ján Profant

The recently proposed VBx diarization method uses a Bayesian hidden Markov model to find speaker clusters in a sequence of x-vectors. In this work we perform an extensive comparison of performance of the VBx diarization with other approaches in the l

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eb987793af3df18b9c97c7fc2eaf971b
http://arxiv.org/abs/2012.14952

Zobrazit plný text záznamu

Analysis of the BUT Diarization System for VoxConverse Challenge

Autor: Lukas Burget, Johan Rohdin, Ondrej Glembek, Federico Landini, Mireia Diez, Anna Silnova, Pavel Matejka

Publikováno v: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
ICASSP

This paper describes the system developed by the BUT team for the fourth track of the VoxCeleb Speaker Recognition Challenge, focusing on diarization on the VoxConverse dataset. The system consists of signal pre-processing, voice activity detection,

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5703904c600ac98f68a352ebe57fd6ce
http://arxiv.org/abs/2010.11718

Zobrazit plný text záznamu

Optimizing Bayesian Hmm Based X-Vector Clustering for the Second Dihard Speech Diarization Challenge

Autor: Honza Cernocky, Lukas Burget, Federico Landini, Shuai Wang, Mireia Diez

Publikováno v: ICASSP

This paper presents an analysis of our diarization system winning the second DIHARD speech diarization challenge, track 1. This system is based on clustering x-vector speaker embeddings extracted every 0.25s from short segments of the input recording

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::823edaf69a727fb1623624ef8749c1e3
https://doi.org/10.1109/icassp40776.2020.9053982

Zobrazit plný text záznamu

BUT System for the Second DIHARD Speech Diarization Challenge

Autor: Lukas Burget, Ondrej Novotny, Johan Rohdin, Oldrich Plchot, Hossein Zeinali, Shuai Wang, Federico Landini, Katerina Zmolikova, Pavel Matejka, Ladislav Mosner, Anna Silnova, Mireia Diez

Publikováno v: Web of Science
ICASSP

This paper describes the winning systems developed by the BUT team for the four tracks of the Second DIHARD Speech Diarization Challenge. For tracks 1 and 2 the systems were mainly based on performing agglomerative hierarchical clustering (AHC) of x-

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0af6d16427ec61340f4a914616b285a5
http://arxiv.org/abs/2002.11356

Zobrazit plný text záznamu

Analysis of ABC Submission to NIST SRE 2019 CMN and VAST Challenge

Publikováno v: Biblos-e Archivo. Repositorio Institucional de la UAM
Universidad Camilo José Cela (UCJC)
Odyssey 2020 The Speaker and Language Recognition Workshop
Odyssey

We present a condensed description and analysis of the joint submission of ABC team for NIST SRE 2019, by BUT, CRIM, Phonexia, Omilia and UAM. We concentrate on challenges that arose during development and we analyze the results obtained on the evalu

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8ab733e54bbc9257b44dee70b4c082f9
http://hdl.handle.net/10486/703093

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání