{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T11:17:55Z","timestamp":1743074275847,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":15,"publisher":"Springer Singapore","isbn-type":[{"type":"print","value":"9789811597343"},{"type":"electronic","value":"9789811597350"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-981-15-9735-0_18","type":"book-chapter","created":{"date-parts":[[2021,1,30]],"date-time":"2021-01-30T07:02:43Z","timestamp":1611990163000},"page":"367-377","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Gender Aware CNN for Speech Emotion Recognition"],"prefix":"10.1007","author":[{"given":"Chinmay","family":"Thakare","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Neetesh Kumar","family":"Chaurasia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Darshan","family":"Rathod","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gargi","family":"Joshi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Santwana","family":"Gudadhe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,1,31]]},"reference":[{"key":"18_CR1","volume-title":"Handbook of cognition and emotion","author":"P Ekman","year":"1999","unstructured":"Ekman, P., & Power, M. J. (1999). Handbook of cognition and emotion. Sussex: Wiley ."},{"issue":"3","key":"18_CR2","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1016\/j.patcog.2010.09.020","volume":"44","author":"M El Ayadi","year":"2011","unstructured":"El Ayadi, M., Kamel, M. S., & Karray, F. (2011). Survey on speech emotion recognition: Features, classification schemes, and databases. Pattern Recognition, 44(3), 572\u2013587.","journal-title":"Pattern Recognition"},{"key":"18_CR3","unstructured":"Vogt, T., & Andre, E. (2006). Improving automatic emotion recognition from speech via gender differentiation. In: Language Resources and Evaluation Conference, Genoa."},{"key":"18_CR4","doi-asserted-by":"publisher","unstructured":"Zhang, L., Wang, L., Dang, J., Guo, L., & Yu, Q (2018). Gender-Aware CNN-BLSTM for Speech Emotion Recognition. In V. Kurkova et al. (Eds.) ICANN 2018, LNCS 11139 (pp. 782\u2013790). https:\/\/doi.org\/10.1007\/978-3-030-01418-6_76.","DOI":"10.1007\/978-3-030-01418-6_76."},{"key":"18_CR5","unstructured":"Nayak B., & Pradhan, M. K. (2016). Text-dependent versus text-independent speech emotion recognition. In Satapathy, S., Raju, K., Mandal, J., Bhateja, V. (Eds.) Proceedings of the Second International Conference on Computer and Communication Technologies. Advances in Intelligent Systems and Computing (vol 379.). New Delhi: Springer."},{"key":"18_CR6","unstructured":"Chen, C., You, M., Song, M., Bu, J., & Liu, J. (2006). An enhanced speech emotion recognition system based on discourse information. In Alexandrov, V. N., van Albada, G. D., Sloot, P. M. A., Dongarra, J. (Eds.) Computational Science \u2013 ICCS 2006. ICCS 2006. Lecture Notes in Computer Science (vol. 3991). Berlin, Heidelberg: Springer."},{"key":"18_CR7","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1007\/s10772-020-09672-4","volume":"23","author":"A Koduru","year":"2020","unstructured":"Koduru, A., Valiveti, H. B., & Budati, A. K. (2020). Feature extraction algorithms to improve the speech emotion recognition rate. International Journal of Speech Technology, 23, 45\u201355. https:\/\/doi.org\/10.1007\/s10772-020-09672-4.","journal-title":"International Journal of Speech Technology"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Zheng, L., Li, Q., Ban, H., &Liu, S. (2018). Speech emotion recognition based on convolution neural networks combined with random forest. In 2018 Chinese Control and Decision Conference (CCDC), Shenyang (pp. 4143\u20134147).","DOI":"10.1109\/CCDC.2018.8407844"},{"key":"18_CR9","unstructured":"Das Mandal, S. K. (2020). NPTEL courses: Digital speech processing, NPTEL: National Programme on Technology Enhanced Learning. Retrieved at April 10, 2020. From the website https:\/\/nptel.ac.in\/courses\/117105145\/."},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Davis, S., & Mermelstein, P. (1980, August). Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Transactions on Acoustics, Speech Signal Processing, 28(4), 357\u2013366.","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"18_CR11","doi-asserted-by":"publisher","unstructured":"Harte, C., Sandler, M., & Gasser, M. (2006). Detecting harmonic change in musical audio. In Proceedings of the 1st ACM Workshop on Audio and Music Computing Multimedia (pp. 21\u201326). Santa Barbara, CA: ACM Press. https:\/\/doi.org\/10.1145\/1178723.1178727.","DOI":"10.1145\/1178723.1178727"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Jiang, D.-N., et al. (2002). Music type classification by spectral contrast feature. In Proceedings. IEEE International Conference on Multimedia and Expo (vol. 1, pp. 113\u2013116).","DOI":"10.1109\/ICME.2002.1035731"},{"key":"18_CR13","unstructured":"Ellis, D. P. W. (2007). Classifying music audio with timbral and chroma features. ISMIR."},{"key":"18_CR14","unstructured":"Haq, S., Jackson, P. J. B., & Edge, J. D. (2008). Audio-visual feature selection and reduction for emotion classification. In Proceedings of the International Conference on Auditory-Visual Speech Processing (pp. 185\u2013190)."},{"issue":"5","key":"18_CR15","doi-asserted-by":"publisher","first-page":"e0196391","DOI":"10.1371\/journal.pone.0196391","volume":"13","author":"SR Livingstone","year":"2018","unstructured":"Livingstone, S. R., & Russo, F. A. (2018). The Ryerson audio-visual database of emotional speech and song (RAVDESS): A dynamic, multimodal set of facial and vocal expressions in North American English. PLoS ONE, 13(5), e0196391. https:\/\/doi.org\/10.1371\/journal.pone.0196391.","journal-title":"PLoS ONE"}],"container-title":["Studies in Computational Intelligence","Health Informatics: A Computational Perspective in Healthcare"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-15-9735-0_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,1,30]],"date-time":"2021-01-30T07:08:35Z","timestamp":1611990515000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-981-15-9735-0_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9789811597343","9789811597350"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-981-15-9735-0_18","relation":{},"ISSN":["1860-949X","1860-9503"],"issn-type":[{"type":"print","value":"1860-949X"},{"type":"electronic","value":"1860-9503"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"31 January 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}