Cooperative learning and its application to emotion recognition from speech. Zhang, Z., Coutinho, E., Deng, J., & Schuller, B. IEEE/ACM Transactions on Audio Speech and Language Processing, 23(1):115-126, 1, 2015.
Cooperative learning and its application to emotion recognition from speech [link]Website  doi  abstract   bibtex   
In this paper, we propose a novel method for highly efficient exploitation of unlabeled data-Cooperative Learning. Our approach consists of combining Active Learning and Semi-Supervised Learning techniques, with the aim of reducing the costly effects of human annotation. The core underlying idea of Cooperative Learning is to share the labeling work between human and machine efficiently in such a way that instances predicted with insufficient confidence value are subject to human labeling, and those with high confidence values are machine labeled. We conducted various test runs on two emotion recognition tasks with a variable number of initial supervised training instances and two different feature sets. The results show that Cooperative Learning consistently outperforms individual Active and Semi-Supervised Learning techniques in all test cases. In particular, we show that our method based on the combination of Active Learning and Co-Training leads to the same performance of a model trained on the whole training set, but using 75% fewer labeled instances. Therefore, our method efficiently and robustly reduces the need for human annotations.
@article{
 title = {Cooperative learning and its application to emotion recognition from speech},
 type = {article},
 year = {2015},
 keywords = {article,journal},
 pages = {115-126},
 volume = {23},
 websites = {http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000348070700011&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=f3ec48df247ee1138ccd8d3ba59bacc2 http://ieeexplore.ieee.org/document/6971},
 month = {1},
 id = {b9377466-8ba0-3199-97bb-ca60b014716a},
 created = {2020-05-29T11:51:38.695Z},
 file_attached = {true},
 profile_id = {ffa9027c-806a-3827-93a1-02c42eb146a1},
 last_modified = {2020-06-08T17:31:31.997Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {zhang2015cooperativespeech},
 source_type = {JOUR},
 folder_uuids = {116db2f1-e6ac-4780-bccf-a977325250cd,99880aa7-55df-4b45-bfce-0ffc00b23ced},
 private_publication = {false},
 abstract = {In this paper, we propose a novel method for highly efficient exploitation of unlabeled data-Cooperative Learning. Our approach consists of combining Active Learning and Semi-Supervised Learning techniques, with the aim of reducing the costly effects of human annotation. The core underlying idea of Cooperative Learning is to share the labeling work between human and machine efficiently in such a way that instances predicted with insufficient confidence value are subject to human labeling, and those with high confidence values are machine labeled. We conducted various test runs on two emotion recognition tasks with a variable number of initial supervised training instances and two different feature sets. The results show that Cooperative Learning consistently outperforms individual Active and Semi-Supervised Learning techniques in all test cases. In particular, we show that our method based on the combination of Active Learning and Co-Training leads to the same performance of a model trained on the whole training set, but using 75% fewer labeled instances. Therefore, our method efficiently and robustly reduces the need for human annotations.},
 bibtype = {article},
 author = {Zhang, Zixing and Coutinho, Eduardo and Deng, Jun and Schuller, Björn},
 doi = {10.1109/TASLP.2014.2375558},
 journal = {IEEE/ACM Transactions on Audio Speech and Language Processing},
 number = {1}
}
Downloads: 0
About
Documentation
Keywords
Search
Users
Terms and Conditions of Use
Privacy Policy
Sitemap
© BibBase.org 2021