Utterance-level aggregation for speaker recognition in the wild

Utterance-level aggregation for speaker recognition in the wild

The objective of this paper is speaker recognition `in the wild' - where utterances may be of variable length and also contain irrelevant signals. Crucial elements in the design of deep networks for this task are the type of trunk (frame level) network, and the method of temporal aggregation. W...

Fuld beskrivelse

Bibliografiske detaljer
Main Authors:	Xie, W, Nagrani, A, Chung, J, Zisserman, A
Format:	Conference item
Udgivet:	IEEE 2019

Lignende værker

Voxceleb: large-scale speaker verification in the wild
af: Nagrani, A, et al.
Udgivet: (2019)

Spot the conversation: Speaker diarisation in the wild
af: Chung, JS, et al.
Udgivet: (2020)

VoxCeleb2: Deep speaker recognition
af: Chung, J, et al.
Udgivet: (2018)

The VoxCeleb speaker recognition challenge: a retrospective
af: Huh, J, et al.
Udgivet: (2024)

VoxCeleb: a large-scale speaker identification dataset
af: Nagrani, A, et al.
Udgivet: (2017)

Emotion Recognition in Speech using Cross-Modal Transfer in the Wild
af: Albanie, S, et al.
Udgivet: (2018)

Emotion recognition in speech using cross-modal transfer in the wild
af: Albanie, S, et al.
Udgivet: (2018)

Count, crop and recognise: fine-grained recognition in the wild
af: Bain, M, et al.
Udgivet: (2020)

Audio-visual synchronisation in the wild
af: Chen, H, et al.
Udgivet: (2021)

Chimpanzee face recognition from videos in the wild using deep learning
af: Schofield, D, et al.
Udgivet: (2019)

Self-supervised utterance order prediction for emotion recognition in conversations
af: Jiang, Dazhi, et al.
Udgivet: (2024)

Playing a part: speaker verification at the movies
af: Brown, A, et al.
Udgivet: (2021)

Forgiving as a performative utterance
af: Swinburne, R
Udgivet: (2021)

Automatic utterance segmentation in spontaneous speech
af: Yoshida, Norimasa, 1979-
Udgivet: (2006)

The anatomy of meaning : speech, gesture, and composite utterances /
af: 443456 Enfield, N. J.
Udgivet: (2009)

Lip reading in the wild
af: Chung, J, et al.
Udgivet: (2017)

Forensic speaker recognition
af: Bonstre, Jean-Francois, et al.
Udgivet: (2010)

Speaker recognition application
af: Li, Yao Dong.
Udgivet: (2013)

Speaker recognition system
af: Song, Liyan.
Udgivet: (2012)

Understanding utterances : The need for pragmatic competence / Kamisah Ariffin
af: Ariffin, Kamisah
Udgivet: (2004)

Acoustic measurements for speaker recognition.
af: Wolf, Jared John
Udgivet: (2005)

Mobile phone speaker recognition
af: Thang, Hui Ru.
Udgivet: (2013)

Speech intelligiblity and speaker recognition/
af: Hawley, Mones E.
Udgivet: (1977)

Out of time: automated lip sync in the wild
af: Chung, J, et al.
Udgivet: (2017)

It's about time: analog clock reading in the wild
af: Yang, C, et al.
Udgivet: (2022)

Slow-fast auditory streams for audio recognition
af: Kazakos, E, et al.
Udgivet: (2021)

Lip Reading Sentences in the Wild
af: Chung, J, et al.
Udgivet: (2017)

Single channel speech separation with constrained utterance level permutation invariant training using grid LSTM
af: Xu, Chenglin, et al.
Udgivet: (2020)

Two-Word Usage: Cognitive Development And The Beginnings Of Combinatorial Utterance.
af: Zakaria, Noraizzah Haji
Udgivet: (1990)

Azuichi, short utterance and responses in Japanese conversation on interview context
af: Shariff, Muhammad Haikal, et al.
Udgivet: (2015)

Utterance verification in large vocabulary spoken language understanding system
af: Yao, Huan, 1976-
Udgivet: (2009)

Processing of speech utterances for computer aided training of speaking skills
af: Zhao, Sixuan
Udgivet: (2014)

Tonal coarticulation in Thai disyllabic utterances: a preliminary study
af: Gandour, Jack, et al.
Udgivet: (2024)

Amodal ground truth and completion in the wild
af: Zhan, G, et al.
Udgivet: (2024)

Design of a speaker recognition system
af: Zhao, Guangye
Udgivet: (2019)

Speaker recognition using neural network
af: Zul Rasyied, Ab. Rasat
Udgivet: (2012)

ASR dependent techniques for speaker recognition
af: Park, Alex S. (Alex Seungryong), 1979-
Udgivet: (2014)

Speaker independent continuous speech recognition
af: Soon, Ing Yann.
Udgivet: (2012)

Mobile phone speaker recognition application
af: Wong, Joseph Pin Jie
Udgivet: (2015)

Mobile phone speaker recognition application
af: Tan, Xavier Junjie
Udgivet: (2014)