{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:26:57Z","timestamp":1775665617628,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1109\/icassp.2016.7472619","type":"proceedings-article","created":{"date-parts":[[2016,6,24]],"date-time":"2016-06-24T01:58:30Z","timestamp":1466733510000},"page":"4950-4954","source":"Crossref","is-referenced-by-count":80,"title":["Deep convolutional acoustic word embeddings using word-pair side information"],"prefix":"10.1109","author":[{"given":"Herman","family":"Kamper","sequence":"first","affiliation":[]},{"given":"Weiran","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Karen","family":"Livescu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Re-source configurable spoken query detection using deep Boltzmann machines","author":"zhang","year":"2012","journal-title":"Proc ICASSP"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639241"},{"key":"ref12","article-title":"Unsu-pervised neural network based feature extraction using weak top-down constraints","author":"kamper","year":"2015","journal-title":"Proc ICASSP"},{"key":"ref13","article-title":"A hybrid dynamic time warping-deep neural network architecture for unsupervised acoustic modeling","author":"thiolliere","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1978.1163164"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179089"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-304","article-title":"Rapid evaluation of speech representations for spoken term discovery","author":"carlin","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001493000339"},{"key":"ref18","article-title":"Fully unsupervised small-vocabulary speech recognition using a segmental Bayesian model","author":"kamper","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref19","article-title":"A comparison of neural network methods for unsupervised representation learning on the Zero Resource Speech Challenge","author":"renshaw","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.25080\/Majora-92bf1922-003","article-title":"Theano: a CPU and GPU math expression compiler","author":"bergstra","year":"2010","journal-title":"Proc SciPy"},{"key":"ref4","article-title":"Word embeddings for speech recognition","author":"bengio","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078558"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707765"},{"key":"ref6","article-title":"Word-level acoustic modeling with convolutional vector regression","author":"maas","year":"2012","journal-title":"Proc ICML Workshop on Representation Learning"},{"key":"ref29","article-title":"ADADELTA: An adaptive learning rate method","author":"zeiler","year":"2012","journal-title":"arXiv preprint arXiv 1212 5701"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178970"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1981.1163586"},{"key":"ref7","article-title":"Generating hyperdimensional distributed representations from continuous-valued multivariate sensory input","author":"rasanen","year":"2015","journal-title":"Proc COGSCII"},{"key":"ref2","article-title":"In-vestigations on exemplar-based features for speech recognition towards thousands of hours of unsupervised, noisy data","author":"heigold","year":"2012","journal-title":"Proc ICASSP"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372931"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.894524"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.909282"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855085"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163965"},{"key":"ref24","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"arXiv preprint arXiv 1301 3781"},{"key":"ref23","article-title":"Learning deep structured semantic models for web search using clickthrough data","author":"huang","year":"2013","journal-title":"Proc CIM"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref25","first-page":"345","article-title":"From paraphrase database to compositional paraphrase model and back","volume":"3","author":"wieting","year":"2015","journal-title":"Trans AC"}],"event":{"name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Shanghai","start":{"date-parts":[[2016,3,20]]},"end":{"date-parts":[[2016,3,25]]}},"container-title":["2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7465907\/7471614\/07472619.pdf?arnumber=7472619","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,17]],"date-time":"2024-06-17T21:25:05Z","timestamp":1718659505000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7472619\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp.2016.7472619","relation":{},"subject":[],"published":{"date-parts":[[2016,3]]}}}