{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:35:09Z","timestamp":1776882909694,"version":"3.51.2"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031162695","type":"print"},{"value":"9783031162701","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-16270-1_30","type":"book-chapter","created":{"date-parts":[[2022,9,15]],"date-time":"2022-09-15T09:30:11Z","timestamp":1663234211000},"page":"364-376","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Sub 8-Bit Quantization of\u00a0Streaming Keyword Spotting Models for\u00a0Embedded Chipsets"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3247-3844","authenticated-orcid":false,"given":"Lu","family":"Zeng","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5368-8860","authenticated-orcid":false,"given":"Sree Hari Krishnan","family":"Parthasarathi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4100-6719","authenticated-orcid":false,"given":"Yuzong","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2683-624X","authenticated-orcid":false,"given":"Alex","family":"Escott","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1144-4507","authenticated-orcid":false,"given":"Santosh","family":"Cheekatmalla","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9295-7859","authenticated-orcid":false,"given":"Nikko","family":"Strom","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2709-5145","authenticated-orcid":false,"given":"Shiv","family":"Vitaladevuni","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,9,16]]},"reference":[{"key":"30_CR1","unstructured":"Agarap, A.F.: Deep learning using rectified linear units (ReLU). arXiv preprint arXiv:1803.08375 (2018)"},{"key":"30_CR2","unstructured":"Banner, R., Hubara, I., Hoffer, E., Soudry, D.: Scalable methods for 8-bit training of neural networks. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"30_CR3","unstructured":"Bengio, Y., L\u00e9onard, N., Courville, A.: Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432 (2013)"},{"key":"30_CR4","unstructured":"Blouw, P., Malik, G., Morcos, B., Voelker, A.R., Eliasmith, C.: Hardware aware training for efficient keyword spotting on general purpose and specialized hardware. arXiv preprint arXiv:2009.04465 (2020)"},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Chen, G., Parada, C., Heigold, G.: Small-footprint keyword spotting using deep neural networks. In: Proceedings of ICASSP (2014)","DOI":"10.1109\/ICASSP.2014.6854370"},{"key":"30_CR6","unstructured":"Courbariaux, M., Bengio, Y., David, J.P.: BinaryConnect: training deep neural networks with binary weights during propagations. In: Advances in Neural Information Processing Systems, pp. 3123\u20133131 (2015)"},{"key":"30_CR7","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.neunet.2017.12.012","volume":"107","author":"S Elfwing","year":"2018","unstructured":"Elfwing, S., Uchibe, E., Doya, K.: Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural Netw. 107, 3\u201311 (2018)","journal-title":"Neural Netw."},{"key":"30_CR8","doi-asserted-by":"crossref","unstructured":"Gao, Y., et al.: On front-end gain invariant modeling for wake word spotting. arXiv preprint arXiv:2010.06676 (2020)","DOI":"10.21437\/Interspeech.2020-1992"},{"key":"30_CR9","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian error linear units (GELUS). arXiv preprint arXiv:1606.08415 (2016)"},{"key":"30_CR10","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448\u2013456 (2015)"},{"key":"30_CR11","unstructured":"Jang, E., Gu, S., Poole, B.: Categorical reparameterization with Gumbel-softmax. arXiv preprint arXiv:1611.01144 (2016)"},{"key":"30_CR12","doi-asserted-by":"crossref","unstructured":"Jose, C., Mishchenko, Y., Senechal, T., Shah, A., Escott, A., Vitaladevuni, S.: Accurate detection of wake word start and end using a CNN. In: InterSpeech (2020)","DOI":"10.21437\/Interspeech.2020-1491"},{"key":"30_CR13","doi-asserted-by":"crossref","unstructured":"Li, X., Wei, X., Qin, X.: Small-footprint keyword spotting with multi-scale temporal convolution. arXiv preprint arXiv:2010.09960 (2020)","DOI":"10.21437\/Interspeech.2020-3177"},{"key":"30_CR14","doi-asserted-by":"crossref","unstructured":"Mishchenko, Y., et al.: Low-bit quantization and quantization-aware training for small-footprint keyword spotting. In: Proceedings of IEEE International Conference On Machine Learning and Applications (ICMLA) (2019)","DOI":"10.1109\/ICMLA.2019.00127"},{"key":"30_CR15","doi-asserted-by":"crossref","unstructured":"Mittermaier, S., K\u00fcrzinger, L., Waschneck, B., Rigoll, G.: Small-footprint keyword spotting on raw audio data with SINC-convolutions. In: Proceedings of ICASSP (2020)","DOI":"10.1109\/ICASSP40776.2020.9053395"},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Nguyen, H.D., Alexandridis, A., Mouchtaris, A.: Quantization aware training with absolute-cosine regularization for automatic speech recognition. In: Proceedings of InterSpeech (2020)","DOI":"10.21437\/Interspeech.2020-1991"},{"key":"30_CR17","doi-asserted-by":"crossref","unstructured":"Panchapagesan, S., et al.: Multi-task learning and weighted cross-entropy for DNN-based keyword spotting. In: Proceedings of InterSpeech (2016)","DOI":"10.21437\/Interspeech.2016-1485"},{"key":"30_CR18","doi-asserted-by":"crossref","unstructured":"Prabhavalkar, R., Alsharif, O., Bruguier, A., McGraw, L.: On the compression of recurrent neural networks with an application to LVCSR acoustic modeling for embedded speech recognition. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5970\u20135974. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472823"},{"key":"30_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1007\/978-3-319-46493-0_32","volume-title":"Computer Vision \u2013 ECCV 2016","author":"M Rastegari","year":"2016","unstructured":"Rastegari, M., Ordonez, V., Redmon, J., Farhadi, A.: XNOR-net: imagenet classification using binary convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 525\u2013542. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_32"},{"key":"30_CR20","doi-asserted-by":"crossref","unstructured":"Shi, B., Sun, M., Kao, C.C., Rozgic, V., Matsoukas, S., Wang, C.: Compression of acoustic event detection models with low-rank matrix factorization and quantization training. arXiv preprint arXiv:1905.00855 (2019)","DOI":"10.21437\/Interspeech.2019-1747"},{"key":"30_CR21","doi-asserted-by":"crossref","unstructured":"Strom, N., Khan, H., Hamza, W.: Squashed weight distribution for low bit quantization of deep models. In: Submitted to Proceedings of InterSpeech (2022)","DOI":"10.21437\/Interspeech.2022-50"},{"key":"30_CR22","doi-asserted-by":"crossref","unstructured":"Sun, M., et al.: Compressed time delay neural network for small-footprint keyword spotting. In: InterSpeech (2017)","DOI":"10.21437\/Interspeech.2017-480"},{"key":"30_CR23","doi-asserted-by":"crossref","unstructured":"Sun, M., et al.: Compressed time delay neural network for small-footprint keyword spotting. In: Proceedings of InterSpeech (2017)","DOI":"10.21437\/Interspeech.2017-480"},{"key":"30_CR24","doi-asserted-by":"crossref","unstructured":"Tucker, G., Wu, M., Sun, M., Panchapagesan, S., Fu, G., Vitaladevuni, S.: Model compression applied to small-footprint keyword spotting. In: Proceedings of InterSpeech (2016)","DOI":"10.21437\/Interspeech.2016-1393"},{"key":"30_CR25","doi-asserted-by":"crossref","unstructured":"Vandersteegen, M., Van Beeck, K., Goedem\u00e9, T.: Integer-only CNNs with 4 bit weights and bit-shift quantization scales at full-precision accuracy. Electronics (2021)","DOI":"10.3390\/electronics10222823"},{"key":"30_CR26","unstructured":"Vanhoucke, V., Senior, A., Mao, M.Z.: Improving the speed of neural networks on CPUs. In: Deep Learning and Unsupervised Feature Learning Workshop, NIPS 2011 (2011)"}],"container-title":["Lecture Notes in Computer Science","Text, Speech, and Dialogue"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-16270-1_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,19]],"date-time":"2023-02-19T05:28:54Z","timestamp":1676784534000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-16270-1_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031162695","9783031162701"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-16270-1_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"16 September 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"TSD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Text, Speech, and Dialogue","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brno","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tsd2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.tsdconference.org\/tsd2022\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}