Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Anil Alexander"'
Publikováno v:
Speech Communication. 124:85-95
The present study investigates relationships between voice similarity ratings made by human listeners and comparison scores produced by an automatic speaker recognition system that includes phonetic, perceptually-relevant features in its modelling. T
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f6a6e30e5aa9ee825044b5483e59e64a
https://doi.org/10.1016/j.specom.2020.08.003
https://doi.org/10.1016/j.specom.2020.08.003
Autor:
Claudio Vair, Daniele Colibro, Kevin R. Farrell, Finnian Kelly, Marcel Kockmann, Anil Alexander
Publikováno v:
Voice Biometrics: Technology, trust and security ISBN: 9781785619007
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::91bd82137f4de71a728bf14178c5976f
https://doi.org/10.1049/pbse012e_ch8
https://doi.org/10.1049/pbse012e_ch8
How Automatic Speaker Recognition (ASR) systems ‘perceive’ voice similarity is of increasing relevance in forensic phonetics. Assessing perceived voice similarity is fundamental to the execution of voice parades (analogous to visual parades) to e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b15f5c8dd53b6dfb1c30f47a1268d31d
https://doi.org/10.33774/coe-2021-dqwkx
https://doi.org/10.33774/coe-2021-dqwkx
Publikováno v:
Odyssey
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7fc88e51270b2acfe886f2aba9c0045e
https://doi.org/10.21437/odyssey.2020-57
https://doi.org/10.21437/odyssey.2020-57
In this paper we propose a spoofing countermeasure based on Constant Q-transform (CQT) features with a ResNet embeddings extractor and a Gaussian Mixture Model (GMM) classifier. We present a detailed analysis of this approach using the Logical Access
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______2659::90cd0a1c9396c96719706c8b13b3d11d
https://zenodo.org/record/4043244
https://zenodo.org/record/4043244
Publikováno v:
Odyssey 2020 The Speaker and Language Recognition Workshop: 1-5 November 2020, Tokyo, Japan, 326-332
STARTPAGE=326;ENDPAGE=332;TITLE=Odyssey 2020 The Speaker and Language Recognition Workshop
Odyssey
The Speaker and Language Recognition Workshop (Odyssey 2020)
STARTPAGE=326;ENDPAGE=332;TITLE=Odyssey 2020 The Speaker and Language Recognition Workshop
Odyssey
The Speaker and Language Recognition Workshop (Odyssey 2020)
In this paper we propose a spoofing countermeasure based on Constant Q-transform (CQT) features with a ResNet embeddings extractor and a Gaussian Mixture Model (GMM) classifier. We present a detailed analysis of this approach using the Logical Access
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::458cec34d77b10de5d5fb1ec71216be4
https://dare.uva.nl/personal/pure/en/publications/residual-networks-for-resisting-noise-analysis-of-an-embeddingsbased-spoofing-countermeasure(c8660e12-a553-4508-843b-9e8cfa73ce7a).html
https://dare.uva.nl/personal/pure/en/publications/residual-networks-for-resisting-noise-analysis-of-an-embeddingsbased-spoofing-countermeasure(c8660e12-a553-4508-843b-9e8cfa73ce7a).html
Publikováno v:
Forensic Science International. 146:S101-S106
This paper deals with a procedure to compensate for mismatched recording conditions in forensic speaker recognition, using a statistical score normalization. Bayesian interpretation of the evidence in forensic automatic speaker recognition depends on
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6d4ca0ea1cc77b0caf2f0ad8083c794b
https://doi.org/10.1016/j.forsciint.2004.09.032
https://doi.org/10.1016/j.forsciint.2004.09.032
Publikováno v:
Forensic Science International. 146:S95-S99
In this paper, we analyse mismatched technical conditions in training and testing phases of speaker recognition and their effect on forensic human and automatic speaker recognition. We use perceptual tests performed by non-experts and compare their p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e208c2c494b75cf77634b77b8ebe4448
https://doi.org/10.1016/j.forsciint.2004.09.078
https://doi.org/10.1016/j.forsciint.2004.09.078
Autor:
Arwa El-Sheemy, Anil Alexander, Gary Wood, Oscar Forth, Martin A. Birchall, Habet Madoyan, George Mochloulis, Marina Mat Baki, Owain R. Hughes, Khalid Ghufoor, John S. Rubin, Guri Sandhu
Publikováno v:
European Journal of Surgical Oncology (EJSO). 41:S81-S82
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ca3677a63222b0de8d5be24eb9d4da77
https://doi.org/10.1016/j.ejso.2015.08.085
https://doi.org/10.1016/j.ejso.2015.08.085
The Quantified‐Self: Mobile Analysis to Facilitate Research and Empower Patients with Voice Problems
Publikováno v:
Otolaryngology–Head and Neck Surgery. 149
Objectives:1) Build into a commonly available mobile device the ability to accurately measure the acoustic characteristics of normal and abnormal voices. 2) Build a user interface that allows untrained patients to reproducibly measure the quality of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::373c5fb6260efbdb8d8a972be94105db
https://doi.org/10.1177/0194599813495815a164
https://doi.org/10.1177/0194599813495815a164