{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T19:10:11Z","timestamp":1762542611831},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2016,11,25]],"date-time":"2016-11-25T00:00:00Z","timestamp":1480032000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Sign Process Syst"],"published-print":{"date-parts":[[2018,5]]},"DOI":"10.1007\/s11265-016-1202-x","type":"journal-article","created":{"date-parts":[[2016,11,25]],"date-time":"2016-11-25T12:28:53Z","timestamp":1480076933000},"page":"727-741","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["A Fixed-Point Neural Network Architecture for Speech Applications on Resource Constrained Hardware"],"prefix":"10.1007","volume":"90","author":[{"given":"Mohit","family":"Shah","sequence":"first","affiliation":[]},{"given":"Sairam","family":"Arunachalam","sequence":"additional","affiliation":[]},{"given":"Jingcheng","family":"Wang","sequence":"additional","affiliation":[]},{"given":"David","family":"Blaauw","sequence":"additional","affiliation":[]},{"given":"Dennis","family":"Sylvester","sequence":"additional","affiliation":[]},{"given":"Hun-Seok","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Jae-sun","family":"Seo","sequence":"additional","affiliation":[]},{"given":"Chaitali","family":"Chakrabarti","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,11,25]]},"reference":[{"key":"1202_CR1","doi-asserted-by":"crossref","unstructured":"Su, D., Wu, X., & Xu, L. (2010). GMM-HMM acoustic model training by a two level procedure with gaussian components determined by automatic model selection. In Proceedings of IEEE international conference on acoustics speech and signal processing (pp. 4890\u20134893).","DOI":"10.1109\/ICASSP.2010.5495122"},{"key":"1202_CR2","unstructured":"Sha, F., & Saul, L.K. (2006). Large margin Gaussian mixture modeling for phonetic classification and recognition. In Proceedings of IEEE international conference on acoustics speech and signal processing (pp. 265\u2013268)."},{"key":"1202_CR3","doi-asserted-by":"crossref","unstructured":"Miller, D.R., Kleber, M., Kao, C.-L., Kimball, O., Colthurst, T., Lowe, S.A., Schwartz, R.M., & Gish, H. (2007). Rapid and accurate spoken term detection. In 8th annual conference of the international speech communication association (pp. 314\u2013317).","DOI":"10.21437\/Interspeech.2007-174"},{"key":"1202_CR4","doi-asserted-by":"crossref","unstructured":"Parlak, S., & Saraclar, M. (2008). Spoken term detection for Turkish broadcast news. In Proceedings of IEEE international conference on acoustics, speech and signal processing (pp. 5244\u20135247).","DOI":"10.1109\/ICASSP.2008.4518842"},{"key":"1202_CR5","doi-asserted-by":"crossref","unstructured":"Mamou, J., Ramabhadran, B., & Siohan, O. (2007). Vocabulary independent spoken term detection. In Proceedings of the 30th annual international ACM SIGIR conference on research and development in information retrieval (pp. 615\u2013622).","DOI":"10.1145\/1277741.1277847"},{"key":"1202_CR6","doi-asserted-by":"crossref","unstructured":"Rohlicek, J.R., Russell, W., Roukos, S., & Gish, H. (1989). Continuous hidden Markov modeling for speaker-independent word spotting. In Proceedings of IEEE international confernce on acoustics speech and signal processing (pp. 627\u2013630).","DOI":"10.1109\/ICASSP.1989.266505"},{"key":"1202_CR7","doi-asserted-by":"crossref","unstructured":"Rose, R.C., & Paul, D.B. (1990). A hidden Markov model based keyword recognition system. In Proceedings of IEEE international conference on acoustics speech and signal processing (pp. 129\u2013132).","DOI":"10.1109\/ICASSP.1990.115555"},{"key":"1202_CR8","doi-asserted-by":"crossref","unstructured":"Wilpon, J., Miller, L., & Modi, P. (1991). Improvements and applications for key word recognition using hidden Markov modeling techniques. In Proceedings of IEEE international conference on acoustics speech and signal processing (pp. 309\u2013312).","DOI":"10.1109\/ICASSP.1991.150338"},{"key":"1202_CR9","unstructured":"Silaghi, M.-C., & Bourlard, H. (1999). Iterative posterior-based keyword spotting without filler models. In Proceedings of the IEEE automatic speech recognition and understanding workshop (pp. 213\u2013216)."},{"key":"1202_CR10","unstructured":"Silaghi, M.-C. (2005). Spotting subsequences matching an HMM using the average observation probability criteria with application to keyword spotting. In Proceedings of the national conference on artificial intelligence, (Vol. 20 pp. 1118\u20131123)."},{"key":"1202_CR11","doi-asserted-by":"crossref","unstructured":"Dahl, G.E., Yu, D., Deng, L., & Acero, A. (2011). Large vocabulary continuous speech recognition with context-dependent DBN-HMMs. In Proceedings of IEEE international conference on acoustics speech and signal processing (pp. 4688\u20134691).","DOI":"10.1109\/ICASSP.2011.5947401"},{"key":"1202_CR12","doi-asserted-by":"crossref","unstructured":"Chen, G., Parada, C., & Heigold, G. (2014). Small-footprint keyword spotting using deep neural networks. In Proceedings of IEEE international conference on acoustics speech and signal processing (pp. 4087\u20134091).","DOI":"10.1109\/ICASSP.2014.6854370"},{"issue":"8","key":"1202_CR13","doi-asserted-by":"crossref","first-page":"1656","DOI":"10.1109\/TCSI.2012.2206501","volume":"59","author":"G He","year":"2012","unstructured":"He, G., Sugahara, T., Miyamoto, Y., Fujinaga, T., Noguchi, H., Izumi, S., Kawaguchi, H., & Yoshimoto, M. (2012). A 40 nm 144 mw VLSI processor for real-time 60-kword continuous speech recognition. IEEE Transactions on Circuits and Systems I: Regular Papers, 59(8), 1656\u20131666.","journal-title":"IEEE Transactions on Circuits and Systems I: Regular Papers"},{"issue":"1","key":"1202_CR14","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1109\/JSSC.2014.2367818","volume":"50","author":"M Price","year":"2015","unstructured":"Price, M., Glass, J., & Chandrakasan, A. (2015). A 6mw 5,000 word real-time speech recognizer using WFST models. IEEE Journal of Solid State Circuits, 50(1), 102\u2013112.","journal-title":"IEEE Journal of Solid State Circuits"},{"key":"1202_CR15","doi-asserted-by":"crossref","unstructured":"Shah, M., Wang, J., Blaauw, D., Sylvester, D., Kim, H.-S., & Chakrabarti, C. (2015). A fixed-point neural network for keyword detection on resource constrained hardware. In IEEE workshop on signal processing systems (SiPS) (pp. 1\u20136).","DOI":"10.1109\/SiPS.2015.7345026"},{"key":"1202_CR16","doi-asserted-by":"crossref","unstructured":"Price, P., Fisher, W.M., Bernstein, J., & Pallett, D.S. (1988). The DARPA 1000-word resource management database for continuous speech recognition. In Proceedings of IEEE international conference on acoustics speech and signal processing (pp. 651\u2013654).","DOI":"10.1109\/ICASSP.1988.196669"},{"key":"1202_CR17","unstructured":"Povey, D., Ghoshal, A., Boulianne, G., Burget, L., Glembek, O., Goel, N., Hannemann, M., Motlicek, P., Qian, Y., Schwarz, P., & et al. (2011). The Kaldi speech recognition toolkit. In IEEE 2011 workshop on automatic speech recognition and understanding. no. EPFL-CONF-192584."},{"key":"1202_CR18","doi-asserted-by":"crossref","unstructured":"Rath, S.P., Povey, D., Vesely\u0300, K., & Cernocky\u0300, J. (2013). Improved feature processing for deep neural networks. In INTERSPEECH (pp. 109\u2013113).","DOI":"10.21437\/Interspeech.2013-48"},{"issue":"6","key":"1202_CR19","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton, G., Deng, L., Yu, D., Dahl, G.E., Mohamed, A.-r., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T.N., & et al. (2012). Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Processing Magazine, 29(6), 82\u201397.","journal-title":"IEEE Signal Processing Magazine"},{"key":"1202_CR20","unstructured":"Miao, Y. (2014). Kaldi+ PDNN: building DNN-based ASR systems with Kaldi and PDNN. arXiv: 1401.6984 ."},{"key":"1202_CR21","doi-asserted-by":"crossref","unstructured":"Venkataramani, S., Ranjan, A., Roy, K., & Raghunathan, A. (2014). axNN: energy-efficient neuromorphic systems using approximate computing. In Proceedings of the international symposium on low power electronics and design (pp. 27\u201332).","DOI":"10.1145\/2627369.2627613"},{"issue":"7","key":"1202_CR22","doi-asserted-by":"crossref","first-page":"1145","DOI":"10.1016\/S0031-3203(96)00142-2","volume":"30","author":"AP Bradley","year":"1997","unstructured":"Bradley, A.P. (1997). The use of the area under the roc curve in the evaluation of machine learning algorithms. Pattern Recognition, 30(7), 1145\u20131159.","journal-title":"Pattern Recognition"},{"key":"1202_CR23","doi-asserted-by":"crossref","unstructured":"Morris, A.C., Maier, V., & Green, P.D. (2004). From WER and RIL to MER and WIl: improved evaluation measures for connected speech recognition. In INTERSPEECH (pp. 2765\u2013 2768).","DOI":"10.21437\/Interspeech.2004-668"},{"key":"1202_CR24","unstructured":"Park, S., Bong, K., Shin, D., Lee, J., Choi, S., & Yoo, H.-j. (2015). a1.93TOPS\/w scalable deep learning\/inference processor with tetra-parallel mimd architecture for big-data applications. In IEEE international solid-state circuits conference-(ISSCC) digest of technical papers (pp. 1\u20133)."},{"issue":"4","key":"1202_CR25","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1145\/2644865.2541967","volume":"49","author":"T Chen","year":"2014","unstructured":"Chen, T., Du, Z., Sun, N., Wang, J., Wu, C., Chen, Y., & Temam, O. (2014). Diannao: A small-footprint high-throughput accelerator for ubiquitous machine-learning. ACM Sigplan Notices, 49(4), 269\u2013284.","journal-title":"ACM Sigplan Notices"},{"key":"1202_CR26","unstructured":"Moons, B., & Verhelst, M. (2016). A 0.3-2.6 TOPS\/W, precision-scalable processor for real-time large-scale conv nets, arXiv: 1606.05094 1606.05094 ."},{"key":"1202_CR27","doi-asserted-by":"crossref","unstructured":"Chen, Y.-H., Krishna, T., Emer, J., & Sze, V. (2016). Eyeriss: an energy-efficient reconfigurable accelerator for deep convolutional neural networks. In IEEE international solid state circuits conference (ISSCC) (pp. 262\u2013264).","DOI":"10.1109\/ISSCC.2016.7418007"}],"container-title":["Journal of Signal Processing Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11265-016-1202-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-016-1202-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-016-1202-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,14]],"date-time":"2022-07-14T22:34:56Z","timestamp":1657838096000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11265-016-1202-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,11,25]]},"references-count":27,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2018,5]]}},"alternative-id":["1202"],"URL":"https:\/\/doi.org\/10.1007\/s11265-016-1202-x","relation":{},"ISSN":["1939-8018","1939-8115"],"issn-type":[{"value":"1939-8018","type":"print"},{"value":"1939-8115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,11,25]]}}}