H-VECTORS: Utterance-level Speaker Embedding Using A Hierarchical
Attention Model

H-VECTORS: Utterance-level Speaker Embedding Using A Hierarchical Attention Model

17 October 2019

Thomas Hain

Papers citing "H-VECTORS: Utterance-level Speaker Embedding Using A Hierarchical Attention Model"

9 / 9 papers shown

Title
Tandem Multitask Training of Speaker Diarisation and Speech Recognition for Meeting Transcription Xianrui Zheng Chuxu Zhang P. Woodland 34 16 0 08 Jul 2022
Reliable Visualization for Deep Speaker Recognition Pengqi Li Lantian Li A. Hamdulla Dong Wang HAI 40 9 0 08 Apr 2022
T-vectors: Weakly Supervised Speaker Identification Using Hierarchical Transformer Model Yanpei Shi Mingjie Chen Qiang Huang Thomas Hain 26 5 0 29 Oct 2020
Combination of Deep Speaker Embeddings for Diarisation Guangzhi Sun Chao Zhang P. Woodland 27 20 0 22 Oct 2020
Fine-grained Early Frequency Attention for Deep Speaker Representation Learning Amirhossein Hajavi Ali Etemad 24 2 0 03 Sep 2020
Adaptation Algorithms for Neural Network-Based Speech Recognition: An Overview P. Bell Joachim Fainberg Ondˇrej Klejch Jinyu Li Steve Renals P. Swietojanski 46 74 0 14 Aug 2020
Exploration of Audio Quality Assessment and Anomaly Localisation Using Attention Models Qiang Huang Thomas Hain 23 1 0 16 May 2020
Weakly Supervised Training of Hierarchical Attention Networks for Speaker Identification Yanpei Shi Qiang Huang Thomas Hain 18 2 0 15 May 2020
On deep speaker embeddings for text-independent speaker recognition Sergey Novoselov Andrey Shulipa Ivan Kremnev Alexander Kozlov Vadim Shchemelinin 30 60 0 26 Apr 2018