{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T00:07:05Z","timestamp":1744157225827,"version":"3.37.3"},"reference-count":52,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology of Taiwan","doi-asserted-by":"publisher","award":["MOST 104-2221-E-002-133-MY2","MOST 106-2221-E-002-220"],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Test Research, Jorjin Technologies, III, Egistec, D8AI, Lite-on"},{"name":"NeoVictory Technology Co., Ltd."}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Speech Communication"],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.1016\/j.specom.2018.06.002","type":"journal-article","created":{"date-parts":[[2018,7,2]],"date-time":"2018-07-02T13:54:27Z","timestamp":1530539667000},"page":"106-112","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":44,"special_numbering":"C","title":["Bone-conducted speech enhancement using deep denoising autoencoder"],"prefix":"10.1016","volume":"104","author":[{"given":"Hung-Ping","family":"Liu","sequence":"first","affiliation":[]},{"given":"Yu","family":"Tsao","sequence":"additional","affiliation":[]},{"given":"Chiou-Shann","family":"Fuh","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.specom.2018.06.002_bib0001","unstructured":"ANSI, 1997. American National Standard: Methods for Calculation of the Speech Intelligibility Index: Acoustical Society of America."},{"key":"10.1016\/j.specom.2018.06.002_bib0002","series-title":"Proceedings of the Interspeech","first-page":"3274","article-title":"Speech enhancement and recognition using multi-task learning of long short-term memory recurrent neural networks","author":"Chen","year":"2015"},{"key":"10.1016\/j.specom.2018.06.002_bib0100","series-title":"IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP), 2017","article-title":"Gaussian density guided deep neural network for single-channel speech enhancement","author":"Chai","year":"2017"},{"key":"10.1016\/j.specom.2018.06.002_bib0003","series-title":"Proceedings of the Interspeech","first-page":"2008","article-title":"Conditional generative adversarial networks for speech enhancement and noise-robust speaker verification","author":"Daniel","year":"2017"},{"key":"10.1016\/j.specom.2018.06.002_bib0004","series-title":"Proceedings of the EUSIPCO","first-page":"1978","article-title":"Improved speech recognition in noisy environments by using a throat microphone for accurate voicing detection","author":"Dekens","year":"2010"},{"article-title":"Exploring speech enhancement with generative adversarial networks for robust speech recognition","year":"2017","author":"Donahue","key":"10.1016\/j.specom.2018.06.002_sbref0004"},{"key":"10.1016\/j.specom.2018.06.002_bib0006","series-title":"Proceedings of the ICASSP","first-page":"708","article-title":"Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks","author":"Erdogan","year":"2015"},{"year":"2013","series-title":"Speech Analysis Synthesis and Perception","author":"Flanagan","key":"10.1016\/j.specom.2018.06.002_bib0007"},{"key":"10.1016\/j.specom.2018.06.002_bib0008","series-title":"Proceedings of the Interspeech","doi-asserted-by":"crossref","first-page":"3768","DOI":"10.21437\/Interspeech.2016-211","article-title":"SNR-aware convolutional neural network modeling for speech enhancement","author":"Fu","year":"2016"},{"key":"10.1016\/j.specom.2018.06.002_bib0009","series-title":"Proceedings of the MLSP","article-title":"Complex spectrogram enhancement by convolutional neural network with multi-metrics learning","author":"Fu","year":"2017"},{"issue":"9","key":"10.1016\/j.specom.2018.06.002_bib0010","doi-asserted-by":"crossref","first-page":"1570","DOI":"10.1109\/TASLP.2018.2821903","article-title":"End-to-end waveform utterance enhancement for direct evaluation metrics optimization by fully convolutional neural networks","volume":"26","author":"Fu","year":"2018","journal-title":"IEEE\/ACM Transactions on Audio, Speech and Language Processing (TASLP)"},{"key":"10.1016\/j.specom.2018.06.002_bib0011","unstructured":"Google 2017. Cloud Speech API, https:\/\/cloud.google.com\/speech\/."},{"key":"10.1016\/j.specom.2018.06.002_bib0012","series-title":"Proceedings of the AISTATS","first-page":"315","article-title":"Deep sparse rectifier neural networks","author":"Glorot","year":"2011"},{"issue":"3","key":"10.1016\/j.specom.2018.06.002_bib0013","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1109\/LSP.2003.808549","article-title":"Combining standard and throat microphones for robust speech recognition","volume":"10","author":"Graciarena","year":"2003","journal-title":"IEEE Signal Process. Lett."},{"year":"1995","series-title":"Advances in Spectrum Analysis and Array Processing, 3","author":"Haykin","key":"10.1016\/j.specom.2018.06.002_bib0014"},{"key":"10.1016\/j.specom.2018.06.002_bib0015","unstructured":"Huang, M.W., 2005. Development of Taiwan Mandarin hearing in noise test. Master thesis, Department of speech language pathology and audiology, National Taipei University of Nursing and Health Sciences."},{"key":"10.1016\/j.specom.2018.06.002_bib0016","series-title":"Proceedings of the Interspeech 2015","article-title":"Rapid adaptation for deep neural networks through multi-task learning","author":"Huang","year":"2015"},{"key":"10.1016\/j.specom.2018.06.002_bib0017","doi-asserted-by":"crossref","first-page":"25542","DOI":"10.1109\/ACCESS.2017.2766675","article-title":"Experimental study on extreme learning machine applications for speech enhancement","volume":"5","author":"Hussain","year":"2017","journal-title":"IEEE Access"},{"key":"10.1016\/j.specom.2018.06.002_bib0018","series-title":"Proceedings of the SLT","first-page":"305","article-title":"Speech enhancement using long short-term memory based recurrent neural networks for noise robust speaker verification","volume":"2016","author":"Kolb\u0153k","year":"2016"},{"key":"10.1016\/j.specom.2018.06.002_bib0019","series-title":"Proceedings of the JIMET","first-page":"137","article-title":"The bone conduction microphone parameter measurement architecture and its speech recognition performance analysis","author":"Kuo","year":"2015"},{"key":"10.1016\/j.specom.2018.06.002_bib0020","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0133519","article-title":"Effects of adaptation rate and noise suppression on the intelligibility of compressed-envelope based speech","volume":"10","author":"Lai","year":"2015","journal-title":"PloS One"},{"issue":"7","key":"10.1016\/j.specom.2018.06.002_bib0021","doi-asserted-by":"crossref","first-page":"1568","DOI":"10.1109\/TBME.2016.2613960","article-title":"A deep denoising autoencoder approach to improving the intelligibility of vocoded speech in cochlear implant simulation","volume":"64","author":"Lai","year":"2017","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"10.1016\/j.specom.2018.06.002_bib0022","doi-asserted-by":"crossref","DOI":"10.1097\/AUD.0000000000000537","article-title":"Deep learning-based noise reduction approach to improve speech intelligibility for cochlear implant recipients","author":"Lai","year":"2018","journal-title":"Ear Hear"},{"issue":"4","key":"10.1016\/j.specom.2018.06.002_bib0023","doi-asserted-by":"crossref","first-page":"745","DOI":"10.1109\/TASLP.2014.2304637","article-title":"An overview of noise-robust automatic speech recognition","volume":"22","author":"Li","year":"2014","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.specom.2018.06.002_bib0024","series-title":"Proceedings of the MMSP","first-page":"363","article-title":"Direct filtering for air- and bone-conductive microphones","author":"Liu","year":"2004"},{"year":"2007","series-title":"Speech Enhancement: Theory and Practice","author":"Loizou","key":"10.1016\/j.specom.2018.06.002_bib0025"},{"key":"10.1016\/j.specom.2018.06.002_bib0026","series-title":"Proceedings of the Interspeech","first-page":"885","article-title":"Ensemble modeling of denoising autoencoder for speech spectrum restoration","author":"Lu","year":"2014"},{"key":"10.1016\/j.specom.2018.06.002_bib0027","series-title":"Proceedings of the Interspeech","first-page":"436","article-title":"Speech enhancement based on deep denoising autoencoder","author":"Lu","year":"2013"},{"key":"10.1016\/j.specom.2018.06.002_bib0028","series-title":"Proceedings of the ICML","first-page":"735","article-title":"Deep learning via Hessian-free optimization","author":"Martens","year":"2010"},{"key":"10.1016\/j.specom.2018.06.002_bib0029","series-title":"Proceedings of the ICASSP","article-title":"Adversarial teacher-student learning for unsupervised domain adaptation","author":"Meng","year":"2018"},{"key":"10.1016\/j.specom.2018.06.002_bib0030","series-title":"Proceedings of the ASRU","article-title":"Cross-domain speech recognition using nonparallel corpora with cycle-consistent adversarial networks","author":"Mimura","year":"2017"},{"key":"10.1016\/j.specom.2018.06.002_bib0031","series-title":"Proceedings of the WASPAA","first-page":"200","article-title":"Speech enhancement using extreme learning machines","author":"Odelowo","year":"2017"},{"key":"10.1016\/j.specom.2018.06.002_bib0032","series-title":"Interspeech","first-page":"3642","article-title":"SEGAN: Speech enhancement generative adversarial network","author":"Santiago","year":"2017"},{"key":"10.1016\/j.specom.2018.06.002_bib0033","series-title":"Proceedings of the ECCTD","first-page":"1","article-title":"Quality improvement of bone-conducted speech","author":"Shimamura","year":"2005"},{"key":"10.1016\/j.specom.2018.06.002_bib0034","series-title":"Proceedings of the ISSPIT","first-page":"628","article-title":"Improving bone-conducted speech quality via neural network","author":"Shimamura","year":"2006"},{"key":"10.1016\/j.specom.2018.06.002_bib0035","series-title":"Proceedings of the Interspeech","doi-asserted-by":"crossref","first-page":"3743","DOI":"10.21437\/Interspeech.2016-1284","article-title":"Perception optimized deep denoising autoencoders for speech enhancement","author":"Shivakumar","year":"2016"},{"key":"10.1016\/j.specom.2018.06.002_bib0036","series-title":"Proceedings of the HSCMA","first-page":"136","article-title":"Multiple-target deep learning for LSTM-RNN based speech enhancement","author":"Sun","year":"2017"},{"issue":"7","key":"10.1016\/j.specom.2018.06.002_bib0037","doi-asserted-by":"crossref","first-page":"2125","DOI":"10.1109\/TASL.2011.2114881","article-title":"An algorithm for intelligibility prediction of time\u2013frequency weighted noisy speech","volume":"19","author":"Taal","year":"2011","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.specom.2018.06.002_bib0038","series-title":"Proceeding of the ICASSP","first-page":"4960","article-title":"A noise suppression method for body-conducted soft speech based on non-negative tensor factorization of air- and body-conducted signals","author":"Tajiri","year":"2017"},{"key":"10.1016\/j.specom.2018.06.002_bib0039","first-page":"407","article-title":"A study on restoration of bone-conducted speech with MTF-based and LP-based models","author":"Thang","year":"2006","journal-title":"J. Signal Process."},{"key":"10.1016\/j.specom.2018.06.002_bib0040","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1097\/00003446-200508000-00002","article-title":"Amplitude-mapping effects on speech intelligibility with unilateral and bilateral cochlear implants","volume":"26","author":"van Hoesel","year":"2005","journal-title":"Ear Hear."},{"year":"2017","series-title":"Improving Speaker-Independent Lipreading with Domain-Adversarial Training","author":"Wand","key":"10.1016\/j.specom.2018.06.002_bib0041"},{"year":"2017","series-title":"Supervised Speech Separation Based on Deep Learning: An Overview","author":"Wang","key":"10.1016\/j.specom.2018.06.002_bib0042"},{"key":"10.1016\/j.specom.2018.06.002_bib0043","series-title":"Proceedings of the ICASSP.","article-title":"Unsupervised domain adaptation via domain adversarial training for speaker recognition","author":"Wang","year":"2018"},{"key":"10.1016\/j.specom.2018.06.002_bib0044","series-title":"Proceedings of the NIPS","first-page":"224","article-title":"Cocktail party processing via structured prediction","author":"Wang","year":"2012"},{"issue":"12","key":"10.1016\/j.specom.2018.06.002_bib0045","doi-asserted-by":"crossref","first-page":"1849","DOI":"10.1109\/TASLP.2014.2352935","article-title":"On training targets for supervised speech separation","volume":"22","author":"Wang","year":"2014","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process"},{"key":"10.1016\/j.specom.2018.06.002_bib0046","series-title":"Proceedings of the LVA\/ICA","first-page":"91","article-title":", Speech enhancement with LSTM recurrent neural networks and its application to noise-robust ASR","author":"Weninger","year":"2015"},{"key":"10.1016\/j.specom.2018.06.002_bib0047","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.specom.2014.02.001","article-title":"Wiener filtering based speech enhancement with weighted denoising auto-encoder and noise classification","volume":"60","author":"Xia","year":"2014","journal-title":"Speech Commun."},{"issue":"1","key":"10.1016\/j.specom.2018.06.002_bib0048","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1109\/LSP.2013.2291240","article-title":"An experimental study on speech enhancement based on deep neural networks","volume":"21","author":"Xu","year":"2014","journal-title":"IEEE Signal Process. Lett."},{"key":"10.1016\/j.specom.2018.06.002_bib0049","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1109\/TASLP.2014.2364452","article-title":"A regression approach to speech enhancement based on deep neural networks,","volume":"23","author":"Xu","year":"2015","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process"},{"key":"10.1016\/j.specom.2018.06.002_bib0050","series-title":"Proceedings of the ICASSP","first-page":"781","article-title":"Multi-sensory microphones for robust speech detection, enhancement, and recognition","author":"Zhang","year":"2004"},{"key":"10.1016\/j.specom.2018.06.002_bib0051","series-title":"Proceedings of the ASRU","first-page":"249","article-title":"Air- and bone-conductive inte-grated microphones for robust speech detection and enhancement","author":"Zheng","year":"2003"}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S016763931730345X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S016763931730345X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2018,11,6]],"date-time":"2018-11-06T20:29:47Z","timestamp":1541536187000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S016763931730345X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":52,"alternative-id":["S016763931730345X"],"URL":"https:\/\/doi.org\/10.1016\/j.specom.2018.06.002","relation":{},"ISSN":["0167-6393"],"issn-type":[{"type":"print","value":"0167-6393"}],"subject":[],"published":{"date-parts":[[2018,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Bone-conducted speech enhancement using deep denoising autoencoder","name":"articletitle","label":"Article Title"},{"value":"Speech Communication","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.specom.2018.06.002","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2018 Elsevier B.V. All rights reserved.","name":"copyright","label":"Copyright"}]}}