{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T06:43:35Z","timestamp":1751265815288,"version":"3.28.0"},"reference-count":40,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,7]]},"DOI":"10.1109\/iwobi.2018.8464132","type":"proceedings-article","created":{"date-parts":[[2018,9,13]],"date-time":"2018-09-13T21:48:06Z","timestamp":1536875286000},"page":"1-8","source":"Crossref","is-referenced-by-count":15,"title":["Hybrid Speech Enhancement with Wiener filters and Deep LSTM Denoising Autoencoders"],"prefix":"10.1109","author":[{"given":"Marvin","family":"Coto-Jimenez","sequence":"first","affiliation":[]},{"given":"John","family":"Goddard-Close","sequence":"additional","affiliation":[]},{"given":"Leandro","family":"Di Persia","sequence":"additional","affiliation":[]},{"given":"Hugo","family":"Leonardo Rufiner","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.2307\/3001913"},{"key":"ref38","first-page":"1278","article-title":"Prediction of perceived phonetic distance from critical-band spectra: A first step","author":"klatt","year":"0","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP) 1982"},{"key":"ref33","first-page":"98","article-title":"Adap-tation transforms of auto-associative neural networks as features for speaker verification","author":"thomas","year":"2012","journal-title":"Odyssey"},{"key":"ref32","first-page":"3371","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"pascal","year":"2010","journal-title":"The Journal of Machine Learning Research"},{"key":"ref31","first-page":"115","article-title":"Learning precise timing with LSTM recurrent networks","author":"gers","year":"2002","journal-title":"Journal of Machine Learning Research"},{"key":"ref30","first-page":"799","article-title":"Bidirectional LSTM networks for improved phoneme classification and recognition","author":"graves","year":"2005","journal-title":"Artificial Neural Networks Springer Berlin Heidelberg"},{"key":"ref37","first-page":"765","article-title":"Perceptual evaluation of speech quality (pesq) the new itu standard for end-to-end speech quality assessment part ii: psychoacoustic model","author":"beerends","year":"2002","journal-title":"Journal of the Audio Engineering Society 50 10"},{"key":"ref36","first-page":"1809","article-title":"Improved HNM-based Vocoder for Statistical Synthesizers","author":"erro","year":"0","journal-title":"Proceedings of Interspeech 2011"},{"key":"ref35","first-page":"223","article-title":"The CMU Arctic speech databases","author":"kominek","year":"2004","journal-title":"Proc Fifth ISCA Speech Synthesis Workshop"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582924"},{"key":"ref10","first-page":"3029","article-title":"An algorithm to improve speech recognition in noise for hearing-impaired listeners","author":"healy","year":"0","journal-title":"The Journal of the Acoustical Society of America 2013 134 4"},{"journal-title":"Design and Analysis of Experiments","year":"2017","author":"montgomery","key":"ref40"},{"key":"ref11","first-page":"7398","article-title":"An investigation of deep neural networks for noise robust speech recognition","author":"seltzer","year":"2013","journal-title":"Proc IEEE Conf Acoustics Speech Signal Proc (ICASSP)"},{"key":"ref12","first-page":"4277","article-title":"Applying convolutional neural networks concepts to hybrid NN-HMM model for speech recognition","author":"abdel-hamid","year":"2012","journal-title":"Proc IEEE Conf Acoustics Speech Signal Proc (ICASSP)"},{"key":"ref13","first-page":"7596","article-title":"Audio-visual deep learning for noise robust speech recognition","author":"huang","year":"2013","journal-title":"Proc IEEE Conf Acoustics Speech Signal Proc (ICASSP)"},{"key":"ref14","article-title":"Recurrent Neural Networks for Noise Reduction in Robust ASR","author":"maas","year":"0","journal-title":"Proc Interspeech 2012"},{"journal-title":"Speech Enhancement In Multiple-Noise Conditions using Deep Neural Networks","year":"2016","author":"kumar","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2291240"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853900"},{"key":"ref19","first-page":"482","article-title":"Reverberant speech recognition based on denoising autoencoder","author":"ishii","year":"0","journal-title":"Proceedings of Interspeech 2013"},{"key":"ref28","first-page":"1735","article-title":"Long short-term memory","author":"sepp","year":"1997","journal-title":"Neural Computation 8"},{"key":"ref4","article-title":"Combining spectral feature mapping and multi-channel model-based source separation for noise-robust automatic speech recognition","author":"bagchi","year":"0","journal-title":"Proceedings of the IEEE ASRU"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178816"},{"key":"ref3","article-title":"Ideal ratio mask estimation using deep neural networks for robust speech recognition","author":"narayanan","year":"0","journal-title":"2013 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref6","first-page":"616","article-title":"Robust speech recognition with speech enhanced deep neural networks","author":"du","year":"0","journal-title":"Proceedings INTERSPEECH 2014"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707742"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.21437\/ICSLP.1998-350","article-title":"An effective quality evaluation protocol for speech enhancement algorithms","volume":"7","author":"hansen","year":"1998","journal-title":"Proceedings of the ICSLP"},{"key":"ref8","first-page":"22","article-title":"Recurrent Neural Networks for Noise Reduction in Robust ASR","author":"maas","year":"0","journal-title":"Proceedings of Interspeech 2012"},{"key":"ref7","first-page":"2484","article-title":"Deep neural network based spectral feature mapping for robust speech recognition","author":"han","year":"0","journal-title":"Proceedings of Interspeech 2015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2014.01.001"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639345"},{"key":"ref1","first-page":"4623","article-title":"Deep recurrent de-noising auto-encoder and blind de-reverberation for reverberated speech recognition","author":"weninger","year":"0","journal-title":"Acoustics Speech and Signal Processing (ICASSP) 2014 IEEE"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854661"},{"key":"ref22","first-page":"437","article-title":"Conversational Speech Transcription Using Context-Dependent Deep Neural Networks","author":"seide","year":"0","journal-title":"Proceedings of IN-TERSPEECH 2011"},{"key":"ref21","first-page":"338","article-title":"Music removal by denoising autoencoder in speech recognition","author":"zhao","year":"2015","journal-title":"IEEE Signal and Information Processing Association Annual Summit and Conference (APSIPA)"},{"key":"ref24","first-page":"436","article-title":"Speech enhancement based on deep denoising autoen-coder","author":"lu","year":"0","journal-title":"Proceedings of Interspeech 2013"},{"key":"ref23","first-page":"354","article-title":"Improving automatic speech recognition containing additive noise using deep denoising autoencoders of LSTM networks","author":"cote-jimenez","year":"2016","journal-title":"International Conference on Speech and Computer Springer Cham"},{"key":"ref26","first-page":"1964","article-title":"TTS synthesis with bidirectional LSTM based recurrent neural networks","author":"yuchen","year":"0","journal-title":"Proceedings of Interspeech 2014"},{"key":"ref25","first-page":"629","article-title":"Speech enhancement based on a priori signal to noise estimation","author":"scalart","year":"1996","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"}],"event":{"name":"2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI)","start":{"date-parts":[[2018,7,18]]},"location":"San Carlos","end":{"date-parts":[[2018,7,20]]}},"container-title":["2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8451008\/8464128\/08464132.pdf?arnumber=8464132","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T09:17:57Z","timestamp":1662023877000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8464132\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/iwobi.2018.8464132","relation":{},"subject":[],"published":{"date-parts":[[2018,7]]}}}