{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T10:02:06Z","timestamp":1760608926209,"version":"3.37.3"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2016,12,1]],"date-time":"2016-12-01T00:00:00Z","timestamp":1480550400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Swiss NSF","award":["CRSII2 141903"],"award-info":[{"award-number":["CRSII2 141903"]}]},{"name":"Procurement and Technology Center"},{"name":"Swiss Federal Department of Defence, Civil Protection and Sport"},{"name":"RECOD"},{"DOI":"10.13039\/501100001711","name":"SNSF","doi-asserted-by":"crossref","award":["200021-153507"],"award-info":[{"award-number":["200021-153507"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1109\/taslp.2016.2604566","type":"journal-article","created":{"date-parts":[[2016,8,31]],"date-time":"2016-08-31T20:35:36Z","timestamp":1472675736000},"page":"2301-2312","source":"Crossref","is-referenced-by-count":20,"title":["Composition of Deep and Spiking Neural Networks for Very Low Bit Rate Speech Coding"],"prefix":"10.1109","volume":"24","author":[{"given":"Milos","family":"Cernak","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandros","family":"Lazaridis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Afsaneh","family":"Asaei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philip N.","family":"Garner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"One-Way Transmission Time","year":"2003","key":"ref73"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.3813\/AAA.918896"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"article-title":"Structured transforms for small-footprint deep learning","year":"2015","author":"sindhwani","key":"ref76"},{"key":"ref77","article-title":"Small-footprint deep neural networks with highway connections for speech recognition","volume":"abs 1512 4280","author":"lu","year":"2015","journal-title":"CoRR"},{"article-title":"Distilling the knowledge in a neural network","year":"2015","author":"hinton","key":"ref74"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1982.1163960"},{"key":"ref75","first-page":"1473","article-title":"Compressing deep neural networks using a rank-constrained topology","author":"nakkiran","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref38","first-page":"4","article-title":"A robust 800 bps MBE coder with VQ and MLP","volume":"2","author":"cui","year":"1998","journal-title":"Proc Int Conf Communication Technology"},{"key":"ref78","first-page":"283","article-title":"Deepear: Robust smartphone audio sensing in unconstrained acoustic environments using deep learning","author":"lane","year":"2015","journal-title":"Proc ACM Int Joint Conf Pervasive Ubiquitous Comput"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2509780"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0100549"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1049\/cp:19991111"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1996.549208"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/29.1651"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"482","DOI":"10.1109\/89.326608","article-title":"Fully vector-quantized neural network-based code-excited nonlinear predictive speech coding","volume":"2","author":"wu","year":"1994","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1991.150432"},{"key":"ref34","first-page":"38","article-title":"Complexity reduction of LD-CELP speech coding in prediction of gain using neural networks","volume":"7","author":"sheikhan","year":"2009","journal-title":"World Appl Sci J"},{"key":"ref60","first-page":"131","article-title":"The HMM-based speech synthesis system version 2.0","author":"zen","year":"2007","journal-title":"Proc 6th ISCA Speech Synth Workshop"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref61","first-page":"192","article-title":"Speaker adaptation and the evaluation of speaker similarity in the EMIME speech-to-speech translation project","author":"wester","year":"2010","journal-title":"Proc 7th ISCA Speech Synthesis Workshop"},{"key":"ref63","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc IEEE Workshop Autom Speech Recognit Understanding"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.1990.117117"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.06213"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"937","DOI":"10.1109\/ICASSP.1985.1168147","article-title":"Code-excited linear prediction (CELP): High-quality speech at very low bit rates","volume":"10","author":"schroeder","year":"1985","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"journal-title":"tsylb2","year":"1996","author":"fisher","key":"ref65"},{"article-title":"A simple continuous excitation model for parametric vocoding","year":"2015","author":"garner","key":"ref66"},{"key":"ref29","first-page":"690","article-title":"Prediction in speech coding: the modification of the coding of LPC parameters and nonlinear estimation technique by using ANN","volume":"1","author":"zhen","year":"1996","journal-title":"Proc 3rd Int Conf Signal Process"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"journal-title":"Methods for subjective determination of transmission quality","year":"1996","key":"ref68"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-49127-9_5"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"482","DOI":"10.1109\/89.928913","article-title":"A very low bit rate speech coder based on a recognition\/synthesis paradigm","volume":"9","author":"lee","year":"2001","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/97.335061"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref22","first-page":"891","article-title":"Anytime learning of decision trees","volume":"8","author":"esmeir","year":"2007","journal-title":"J Mach Learn Res"},{"key":"ref21","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"2013","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854318"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.03.003"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1982.1171649"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-23132-7_24"},{"journal-title":"On structured sparsity of phonological posteriors for linguistic parsing","year":"2016","author":"cernak","key":"ref50"},{"key":"ref51","first-page":"94","article-title":"From discontinuous to continuous F0 modelling In HMM-based speech synthesis","author":"yu","year":"2010","journal-title":"Proc 7th ISCA Speech Synthesis Workshop"},{"key":"ref59","article-title":"The festival speech synthesis system","author":"black","year":"1997","journal-title":"Tech Rep"},{"article-title":"DARPA TIMIT acoustic-phonetic continuous speech corpus CD-ROM. NIST speech disc 1-1.1. NASA STI\/Recon technical report, 93, LDC93S1","year":"1993","author":"garofolo","key":"ref58"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-235"},{"key":"ref55","doi-asserted-by":"crossref","first-page":"3449","DOI":"10.21437\/Interspeech.2013-755","article-title":"Syllable-based pitch encoding for low bit rate speech coding with recognition\/synthesis architecture","author":"cernak","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref54","first-page":"1191","article-title":"Neuromorphic based oscillatory device for incremental syllable boundary detection","author":"hyafil","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref53","first-page":"67","article-title":"Using noisy speech to study the robustness of a continuous F0 modelling method in HMM-based speech synthesis","author":"ogbureke","year":"2012","journal-title":"Proc Speech Prosody"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2076805"},{"journal-title":"English Sound Structure","year":"1994","author":"harris","key":"ref10"},{"key":"ref11","first-page":"34","author":"harris","year":"1995","journal-title":"The elements of phonological representation"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1982.1171472"},{"journal-title":"The Sound Pattern of English","year":"1968","author":"chomsky","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288837"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2167610"},{"key":"ref15","first-page":"418","article-title":"On compressibility of neural network phonological features for low bit rate speech coding","author":"asaei","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1561\/2200000006"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3210-1"},{"key":"ref18","article-title":"Deep belief networks for phone recognition","author":"mohamed","year":"2009","journal-title":"Proc NIPS Workshop Deep Learning for Speech Recognition"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1989.266493"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198900"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518530"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.675338"},{"key":"ref8","first-page":"195","article-title":"Linguistic dissection of switchboard-corpus automatic speech recognition systems","author":"greenberg","year":"2000","journal-title":"Proc ISCA Workshop on Automatic Speech Recognition Challenges for the New Millennium"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2418577"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1152\/jn.00263.2005"},{"article-title":"Speech vocoding for laboratory phonology","year":"2016","author":"cernak","key":"ref9"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178891"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3390\/info7020032"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1121\/1.4883366"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2135852"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1983.1172244"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1983.1172241"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/29.90372"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1985.1164584"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7571201\/07557039.pdf?arnumber=7557039","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,19]],"date-time":"2024-06-19T04:22:35Z","timestamp":1718770955000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7557039\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,12]]},"references-count":78,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2016.2604566","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2016,12]]}}}