Filters








1,998 Hits in 6.0 sec

Speaker Attribution with Voice Profiles by Graph-Based Semi-Supervised Learning

Jixuan Wang, Xiong Xiao, Jian Wu, Ranjani Ramamurthy, Frank Rudzicz, Michael Brudno
2020 Interspeech 2020  
In this paper, we propose to solve the speaker attribution problem by using graph-based semi-supervised learning methods.  ...  Speaker attribution then becomes a semi-supervised learning problem on graphs, on which two graph-based methods are applied: label propagation (LP) and graph neural networks (GNNs).  ...  Conclusion In this work, we applied graph-based semi-supervised learning methods for the speaker attribution task with speaker voice profiles.  ... 
doi:10.21437/interspeech.2020-1950 dblp:conf/interspeech/WangXWRRB20 fatcat:v24rgjdqnbfpjgm5lhgw2u2gle

Graph-based Label Propagation for Semi-Supervised Speaker Identification [article]

Long Chen, Venkatesh Ravichandran, Andreas Stolcke
2021 arXiv   pre-print
We propose a graph-based semi-supervised learning approach for speaker identification in the household scenario, to leverage the unlabeled speech samples.  ...  well as their semi-supervised variants based on pseudo-labels.  ...  Semi-supervised learning (SSL) is a technique to reduce the dependency on annotations by learning from unlabeled, as well as labeled, data.  ... 
arXiv:2106.08207v1 fatcat:5kjp7bohtfbp3lqgn3wd2emmwe

Three recent trends in Paralinguistics on the way to omniscient machine intelligence

Björn W. Schuller, Yue Zhang, Felix Weninger
2018 Journal on Multimodal User Interfaces  
While this is not reached at the time for many tasks such as speaker emotion recognition, deep learning-often described to lead to significant improvements-in combination with sufficient learning data,  ...  Smallworld modelling in combination with unsupervised learning help to rapidly identify potential target data of interest.  ...  Cooperative learning: human + machine Aiming to reduce human labelling effort has long since led to the idea of self-learning by machines such as by unsupervised, semi-supervised, or active learning.  ... 
doi:10.1007/s12193-018-0270-6 fatcat:cqlvp4ozmbe6zponscyplel45i

Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things [article]

Jing Zhang, Dacheng Tao
2020 arXiv   pre-print
Then, we present progress in AI research for IoT from four perspectives: perceiving, learning, reasoning, and behaving.  ...  Artificial intelligence (AI), especially deep learning, is now a proven success in various areas including computer vision, speech recognition, and natural language processing.  ...  TIMIT APCSC https://catalog.ldc.upenn.edu/LDC93S1 630 speakers Text, ID Common Voice https://commonvoice.mozilla.org/en/datasets 61,528 voices ID, Attributes widely used calibration method is proposed  ... 
arXiv:2011.08612v1 fatcat:dflut2wdrjb4xojll34c7daol4

A subspace co-training framework for multi-view clustering

Xuran Zhao, Nicholas Evans, Jean-Luc Dugelay
2014 Pattern Recognition Letters  
The new algorithm is flexible and can be readily adapted to use different distance measures, semi-supervised learning, and non-linear problems.  ...  We propose a new algorithm which learns discriminative subspaces in an unsupervised fashion based upon the assumption that a reliable clustering should assign same-class samples to the same cluster in  ...  Co-training Co-training (Blum and Mitchell, 1998) is one of the most acclaimed approaches to semi-supervised learning.  ... 
doi:10.1016/j.patrec.2013.12.003 fatcat:2guqz674afbsxk5kkrt346tvy4

A Review on Voice-based Interface for Human-Robot Interaction

Ameer Badr, Alia Abdul-Hassan
2020 Iraqi Journal for Electrical And Electronic Engineering  
With the recent developments of technology and the advances in artificial intelligence and machine learning techniques, it has become possible for the robot to understand and respond to voice as part of  ...  The voice-based interface robot can recognize the speech information from humans so that it will be able to interact more naturally with its human counterpart in different environments.  ...  ARI is an autonomous or semi-autonomous robot where the robot decision is made based on the awareness of environmental information from the user, where this information may include user profile, user emotions  ... 
doi:10.37917/ijeee.16.2.10 fatcat:crz5ieseo5g5nmcllbpm5oz22e

Motivations, Methods and Metrics of Misinformation Detection: An NLP Perspective

Qi Su, Mingyu Wan, Xiaoqian Liu, Chu-Ren Huang
2020 Natural Language Processing Research  
Advantages and disadvantages of the key techniques are also addressed with focuses on content-based analysis and predicative modeling.  ...  This paper discusses the main issues of misinformation and its detection with a comprehensive review on representative works in terms of detection methods, feature representations, evaluation metrics and  ...  [54] propose a semi-supervised method for content-based detection of misinformation via tensor embeddings.  ... 
doi:10.2991/nlpr.d.200522.001 fatcat:vwwspvaexbga3kn5mxtdo6ke6u

Improving Speech Emotion Recognition Using Graph Attentive Bi-Directional Gated Recurrent Unit Network

Bo-Hao Su, Chun-Min Chang, Yun-Shao Lin, Chi-Chun Lee
2020 Interspeech 2020  
Our proposed GA-GRU combines both long-range time-series based modeling of speech and further integrates complex saliency using a graph structure.  ...  In this work, we propose a framework in imposing a graph attention mechanism on gated recurrent unit network (GA-GRU) to improve utterance-based speech emotion recognition (SER).  ...  Attention and Graph Analysis We provide an analysis on the learned graph-based attention weights.  ... 
doi:10.21437/interspeech.2020-1733 dblp:conf/interspeech/SuCLL20 fatcat:5soj4gpfr5cnpeglq63itm23nu

Audio-Visual Biometric Recognition and Presentation Attack Detection: A Comprehensive Survey [article]

Hareesh Mandalapu, Aravinda Reddy P N, Raghavendra Ramachandra, K Sreenivasa Rao, Pabitra Mitra, S R Mahadeva Prasanna, Christoph Busch
2021 arXiv   pre-print
Amidst the classically used biometrics, voice and face attributes are the most propitious for prevalent applications in day-to-day life because they are easy to obtain through restrained and user-friendly  ...  For many years, acoustic information alone has been a great success in automatic speaker verification applications.  ...  The MSDA is inspired by a multi-view semi-supervised learning method called co-training [19] .  ... 
arXiv:2101.09725v1 fatcat:huejyfaeojhzddlckqt5nfivlq

Audio-Visual Biometric Recognition and Presentation Attack Detection: A Comprehensive Survey

Hareesh Mandalapu, Aravinda Reddy P N, Raghavendra Ramachandra, Krothapalli Sreenivasa Rao, Pabitra Mitra, S. R. Mahadeva Prasanna, Christoph Busch
2021 IEEE Access  
Amidst the classically used biometrics, voice and face attributes are the most propitious for prevalent applications in day-to-day life because they are easy to obtain through restrained and user-friendly  ...  For many years, acoustic information alone has been a great success in automatic speaker verification applications.  ...  The MSDA is inspired by a multi-view semi-supervised learning method called co-training [19] .  ... 
doi:10.1109/access.2021.3063031 fatcat:q6emam55frhlzp53t7lxb4qz3e

CUSTOMER SEGMENTATION AND CLASSIFICATION FROM BLOGS BY USING DATA MINING: AN EXAMPLE OF VOIP PHONE

Long-Sheng Chen, Chun-Chin Hsu, Mu-Chen Chen
2009 Cybernetics and systems  
Then, we can use supervised learning tools to extract knowledge.  ...  (SOM) -Sparsity analysis Step 5: Supervised learning Back-Propagation Neural Network (BPN), C4.5, and (SVM) In step 1, blog mining users need to define a set of keywords to be the variables (attributes  ... 
doi:10.1080/01969720903152593 fatcat:4r5jgv2vgzaebbq2wa4bw7qz3i

CRF-Based Context Modeling for Person Identification in Broadcast Videos

Paul Gay, Sylvain Meignier, Paul Deléglise, Jean-Marc Odobez
2016 Frontiers in ICT  
They choose a learning setting which takes into account 111 the label ambiguities, for example: multiple instance learning (Wohlhart et al. (2011)) and semi-supervised 112 strategies (Bauml et al. (2013  ...  2 We are investigating the problem of speaker and face identification in broadcast videos. 3 Identification is performed by associating automatically extracted names from overlaid texts 4 with speaker  ...  it would be interesting to increase the recall of the face detector, for instance, by adding a profile view 498 detector.  ... 
doi:10.3389/fict.2016.00009 fatcat:emrygzd3uffxtfvu2unctmsw54

Learning Neural Textual Representations for Citation Recommendation

Binh Thanh Kieu, Inigo Jauregi Unanue, Son Bao Pham, Hieu Xuan Phan, Massimo Piccardi
2021 2020 25th International Conference on Pattern Recognition (ICPR)  
Semi-supervised Deep Learning Techniques for Spectrum Reconstruction Hong, Hanbin; Bao, Wentao; Hong, Yuan; Kong, Yu 1187 Privacy Attributes-Aware Message Passing Neural Network for Visual Privacy Attributes  ...  ; Awate, Suyash 1551 Generative Deep-Neural-Network Mixture Modeling with Semi- Supervised MinMax+EM Learning DAY 3 -Jan 14, 2021 Sahoo, Saswata; Chakraborty, Souradip 1559 Graph Spectral Feature  ... 
doi:10.1109/icpr48806.2021.9412725 fatcat:3vge2tpd2zf7jcv5btcixnaikm

Deep Spoken Keyword Spotting: An Overview

Ivan Lopez-Espejo, Zheng-Hua Tan, John Hansen, Jesper Jensen
2021 IEEE Access  
Welling, “Semi-supervised classification with graph [111] H. Muckenhirn, M. Magimai.-Doss, and S.  ...  Tami, “An overview of deep semi- supervised learning,” arXiv:2006.05278v2, 2020. [260] S. Sigtia, E. Marchi, S. Kajarekar, D. Naik, and J.  ... 
doi:10.1109/access.2021.3139508 fatcat:i4pfpfxcpretlkbefp7owtxcti

A Survey on Natural Language Processing for Fake News Detection [article]

Ray Oshikawa, Jing Qian, William Yang Wang
2020 arXiv   pre-print
Based on our insights, we outline promising research directions, including more fine-grained, detailed, fair, and practical detection models.  ...  Machine Learning Models As mentioned in Section 3., the majority of existing research uses supervised methods while semi-supervised or unsupervised methods are less commonly used.  ...  Therefore, semi/weakly-supervised and unsupervised methods are proposed (Rubin and Vashchilko, 2012; Bhattacharjee et al., 2017) .  ... 
arXiv:1811.00770v2 fatcat:muo74knnsfehlmhcopqzivfo6q
« Previous Showing results 1 — 15 out of 1,998 results