{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:29:09Z","timestamp":1750220949165,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,4,16]],"date-time":"2019-04-16T00:00:00Z","timestamp":1555372800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CNS-1816213, CNS-1704469"],"award-info":[{"award-number":["CNS-1816213, CNS-1704469"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,4,16]]},"DOI":"10.1145\/3302506.3310402","type":"proceedings-article","created":{"date-parts":[[2019,4,4]],"date-time":"2019-04-04T18:38:43Z","timestamp":1554403123000},"page":"217-228","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["SoundSemantics"],"prefix":"10.1145","author":[{"given":"Md Tamzeed","family":"Islam","sequence":"first","affiliation":[{"name":"UNC Chapel Hill"}]},{"given":"Shahriar","family":"Nirjon","sequence":"additional","affiliation":[{"name":"UNC Chapel Hill"}]}],"member":"320","published-online":{"date-parts":[[2019,4,16]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Tensorflow. https:\/\/www.tensorflow.org\/lite\/."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157196"},{"key":"e_1_3_2_1_3_1","volume-title":"Acoustic monitoring in terrestrial environments using microphone arrays: applications, technological considerations and prospectus. Journal of Applied Ecology","author":"Blumstein D. T.","year":"2011","unstructured":"Blumstein, D. T., Mennill, D. J., Clemins, P., Girod, L., Yao, K., Patricelli, G., Deffe, J. L., Krakauer, A. H., Clark, C., Cortopassi, K. A., et al. Acoustic monitoring in terrestrial environments using microphone arrays: applications, technological considerations and prospectus. Journal of Applied Ecology (2011)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/11428572_4"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.4108\/icst.pervasivehealth.2013.252148"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521669"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/IoTDI.2018.00031"},{"key":"e_1_3_2_1_8_1","unstructured":"Dedeoglu Y. Toreyin B. U. Gudukbay U. and Cetin A. E. Surveillance using both video and audio. In Multimodal Processing and Interaction."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/2602339.2602352"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/2999792.2999849"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/3086952"},{"key":"e_1_3_2_1_12_1","first-page":"5","article-title":"Energy monitoring in residential spaces with audio sensor nodes","volume":"11","author":"Guvensan M. A.","year":"2013","unstructured":"Guvensan, M. A., Taysi, Z. C., and Melodia, T. Energy monitoring in residential spaces with audio sensor nodes: Tinyears. Ad Hoc Networks 11, 5 (2013), 1539--1555.","journal-title":"Tinyears. Ad Hoc Networks"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.273716"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/2390524.2390645"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3081333.3081338"},{"key":"e_1_3_2_1_18_1","volume-title":"Proc. ICML Workshop on Deep Learning for Audio, Speech and Language","author":"Jaitly N.","year":"2013","unstructured":"Jaitly, N., and Hinton, G. E. Vocal tract length perturbation (vtlp) improves speech recognition. In Proc. ICML Workshop on Deep Learning for Audio, Speech and Language (2013)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/1293951.1293954"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaa8415"},{"volume-title":"Automatic Speech Recognition and Understanding (ASRU), 2013 IEEE Workshop on.","author":"Kanda N.","key":"e_1_3_2_1_21_1","unstructured":"Kanda, N., Takeda, R., and Obuchi, Y. Elastic spectral distortion for low resource speech recognition with deep neural networks. In Automatic Speech Recognition and Understanding (ASRU), 2013 IEEE Workshop on."},{"key":"e_1_3_2_1_22_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma D. P.","year":"2014","unstructured":"Kingma, D. P., and Ba, J. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_23_1","unstructured":"Koch G. Siamese neural networks for one-shot image recognition."},{"key":"e_1_3_2_1_24_1","volume-title":"Semantic autoencoder for zero-shot learning. arXiv preprint arXiv:1704.08345","author":"Kodirov E.","year":"2017","unstructured":"Kodirov, E., Xiang, T., and Gong, S. Semantic autoencoder for zero-shot learning. arXiv preprint arXiv:1704.08345 (2017)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462200"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.982906"},{"key":"e_1_3_2_1_27_1","volume-title":"Decision templates for multiple classifier fusion: an experimental comparison. Pattern recognition","author":"Kuncheva L. I.","year":"2001","unstructured":"Kuncheva, L. I., Bezdek, J. C., and Duin, R. P. Decision templates for multiple classifier fusion: an experimental comparison. Pattern recognition (2001)."},{"key":"e_1_3_2_1_28_1","first-page":"2","volume-title":"IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP 2003","volume":"1","author":"Lamere P.","year":"2003","unstructured":"Lamere, P., Kwok, P., Gouvea, E., Raj, B., Singh, R., Walker, W., Warmuth, M., and Wolf, P. The cmu sphinx-4 speech recognition system. In IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP 2003), Hong Kong (2003), vol. 1, pp. 2--5."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.140"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/2984093.2984217"},{"key":"e_1_3_2_1_31_1","volume-title":"Theory of point estimation","author":"Lehmann E. L.","year":"2006","unstructured":"Lehmann, E. L., and Casella, G. Theory of point estimation. Springer Science & Business Media, 2006."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/2021975.2021992"},{"key":"e_1_3_2_1_33_1","unstructured":"Mikolov T. Chen K. Corrado G. and Dean J. Efficient estimation of word representations in vector space. arXiv preprint."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1814433.1814437"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPSN.2018.00051"},{"key":"e_1_3_2_1_36_1","first-page":"930","volume-title":"INTERSPEECH","author":"Morales N.","year":"2007","unstructured":"Morales, N., Gu, L., and Gao, Y. Adding noise to improve noise robustness in speech recognition. In INTERSPEECH (2007), pp. 930--933."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2462456.2464446"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2426656.2426662"},{"key":"e_1_3_2_1_39_1","unstructured":"Norouzi M. Mikolov T. Bengio S. Singer Y. Shlens J. Frome A. Corrado G. S. and Dean J. Zero-shot learning by convex combination of semantic embeddings."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.5555\/2984093.2984252"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"e_1_3_2_1_42_1","first-page":"128","volume-title":"Wireless Health","author":"Ra H.-K.","year":"2016","unstructured":"Ra, H.-K., Salekin, A., Yoon, H.-J., Kim, J., Nirjon, S. S., Stone, D. J., Kim, S., Lee, J.-M., Son, S. H., Stankovic, J. A., et al. Asthmaguide: an asthma monitoring and advice ecosystem. In Wireless Health (2016), pp. 128--135."},{"key":"e_1_3_2_1_43_1","volume-title":"An overview of classifier fusion methods. Computing and Information systems 7, 1","author":"Ruta D.","year":"2000","unstructured":"Ruta, D., and Gabrys, B. An overview of classifier fusion methods. Computing and Information systems 7, 1 (2000), 1--10."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-831"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3214284"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.5555\/2999611.2999716"},{"key":"e_1_3_2_1_48_1","volume-title":"The calculation of posterior distributions by data augmentation. Journal of the American statistical Association 82, 398","author":"Tanner M. A.","year":"1987","unstructured":"Tanner, M. A., and Wong, W. H. The calculation of posterior distributions by data augmentation. Journal of the American statistical Association 82, 398 (1987), 528--540."},{"key":"e_1_3_2_1_49_1","volume-title":"Learning from between-class examples for deep sound recognition. arXiv preprint arXiv:1711.10282","author":"Tokozume Y.","year":"2017","unstructured":"Tokozume, Y., Ushiku, Y., and Harada, T. Learning from between-class examples for deep sound recognition. arXiv preprint arXiv:1711.10282 (2017)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/11573425_21"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157382.3157504"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/1145287.1145312"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.15"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.474"}],"event":{"name":"IPSN '19: The 18th International Conference on Information Processing in Sensor Networks","sponsor":["SIGBED ACM Special Interest Group on Embedded Systems","IEEE-SPS Signal Processing Society"],"location":"Montreal Quebec Canada","acronym":"IPSN '19"},"container-title":["Proceedings of the 18th International Conference on Information Processing in Sensor Networks"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3302506.3310402","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3302506.3310402","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3302506.3310402","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:53:54Z","timestamp":1750204434000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3302506.3310402"}},"subtitle":["exploiting semantic knowledge in text for embedded acoustic event classification"],"short-title":[],"issued":{"date-parts":[[2019,4,16]]},"references-count":55,"alternative-id":["10.1145\/3302506.3310402","10.1145\/3302506"],"URL":"https:\/\/doi.org\/10.1145\/3302506.3310402","relation":{},"subject":[],"published":{"date-parts":[[2019,4,16]]},"assertion":[{"value":"2019-04-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}