Zobrazeno 1 - 10
of 1 326
pro vyhledávání: '"A Desplanques"'
Automated speaker identification (SID) is a crucial step for the personalization of a wide range of speech-enabled services. Typical SID systems use a symmetric enrollment-verification framework with a single model to derive embeddings both offline f
Externí odkaz:
http://arxiv.org/abs/2401.12440
Publikováno v:
Tribology and Materials, Vol 3, Iss 1, Pp 1-14 (2024)
In this work, the authors tackle the problem of laboratory simulation of frictional contact in wheels-up emergency landing conditions. To design a novel tribometer simulating the contact between an aircraft structure and a runway, one must carry two
Externí odkaz:
https://doaj.org/article/77f1976e3aec4009916b8613318f4a06
This paper contains a post-challenge performance analysis on cross-lingual speaker verification of the IDLab submission to the VoxCeleb Speaker Recognition Challenge 2021 (VoxSRC-21). We show that current speaker embedding extractors consistently und
Externí odkaz:
http://arxiv.org/abs/2110.09150
This technical report describes the IDLab submission for track 1 and 2 of the VoxCeleb Speaker Recognition Challenge 2021 (VoxSRC-21). This speaker verification competition focuses on short duration test recordings and cross-lingual trials. Currently
Externí odkaz:
http://arxiv.org/abs/2109.04070
We present an iVector based Acoustic Scene Classification (ASC) system suited for real life settings where active foreground speech can be present. In the proposed system, each recording is represented by a fixed-length iVector that models the record
Externí odkaz:
http://arxiv.org/abs/2108.00912
This paper describes the IDLab submission for the text-independent task of the Short-duration Speaker Verification Challenge 2021 (SdSVC-21). This speaker verification competition focuses on short duration test recordings and cross-lingual trials, al
Externí odkaz:
http://arxiv.org/abs/2104.02370
Autor:
Dawalatabad, Nauman, Ravanelli, Mirco, Grondin, François, Thienpondt, Jenthe, Desplanques, Brecht, Na, Hwidong
Learning robust speaker embeddings is a crucial step in speaker diarization. Deep neural networks can accurately capture speaker discriminative characteristics and popular deep embeddings such as x-vectors are nowadays a fundamental component of mode
Externí odkaz:
http://arxiv.org/abs/2104.01466
In this technical report we describe the IDLAB top-scoring submissions for the VoxCeleb Speaker Recognition Challenge 2020 (VoxSRC-20) in the supervised and unsupervised speaker verification tracks. For the supervised verification tracks we trained 6
Externí odkaz:
http://arxiv.org/abs/2010.12468
In this paper we propose and analyse a large margin fine-tuning strategy and a quality-aware score calibration in text-independent speaker verification. Large margin fine-tuning is a secondary training stage for DNN based speaker verification systems
Externí odkaz:
http://arxiv.org/abs/2010.11255
In this paper we describe the top-scoring IDLab submission for the text-independent task of the Short-duration Speaker Verification (SdSV) Challenge 2020. The main difficulty of the challenge exists in the large degree of varying phonetic overlap bet
Externí odkaz:
http://arxiv.org/abs/2007.07689