{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T15:27:14Z","timestamp":1771342034320,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8461580","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"5499-5503","source":"Crossref","is-referenced-by-count":18,"title":["3-D CNN Models for Far-Field Multi-Channel Speech Recognition"],"prefix":"10.1109","author":[{"given":"Sriram","family":"Ganapathy","sequence":"first","affiliation":[]},{"given":"Vijayaditya","family":"Peddinti","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref32","first-page":"89","article-title":"Optimization methods for supervised machine learning: From linear models to deep learning","author":"frank e","year":"2017","journal-title":"Leading Developments from INFORMS Communities"},{"key":"ref31","first-page":"8609","article-title":"Im-proving deep neural networks for lvcsr using rectified linear units and dropout","author":"george e","year":"2013","journal-title":"ICASSP IEEE"},{"key":"ref30","first-page":"3857","article-title":"Attention-based LSTM with multi-task learning for distant speech recognition","author":"yu","year":"2017","journal-title":"InterSpeech"},{"key":"ref10","author":"gaofeng","year":"2017","journal-title":"CNN-TDNN-LSTM acoustic models for AMI LVCSR"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"2011","DOI":"10.1109\/TASL.2007.902460","article-title":"Acoustic beamforming for speaker diarization of meetings","volume":"15","author":"xavier","year":"2007","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1109\/TSA.2004.832988","article-title":"Likelihood-maximizing beamforming for robust hands-free speech recognition","volume":"12","author":"michael l","year":"2004","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"1120","DOI":"10.1109\/LSP.2014.2325781","article-title":"Con-volutional neural networks for distant speech recognition","volume":"21","author":"pawel","year":"2014","journal-title":"IEEE Signal Processing Letters"},{"key":"ref14","first-page":"5745","article-title":"Deep beamforming networks for multichannel speech recognition","author":"xiong","year":"2016","journal-title":"ICASSP IEEE"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"965","DOI":"10.1109\/TASLP.2017.2672401","article-title":"Multichannel signal processing with deep neural networks for automatic speech recognition","volume":"25","author":"tara n","year":"2017","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref16","first-page":"1976","article-title":"Neural network adaptive beamforming for robust multichannel speech recognition","author":"bo","year":"2016","journal-title":"InterSpeech"},{"key":"ref17","article-title":"A unified architecture for multichannel end-to-end speech recognition with neural beamforming","author":"tsubasa","year":"2017","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.media.2016.10.004","article-title":"Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation","volume":"36","author":"konstantinos","year":"2017","journal-title":"Medical Image Analysis"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"534","DOI":"10.1109\/TASL.2008.2009015","article-title":"Suppression of late reverberation effect on speech signal using long-term multiple-step linear prediction","volume":"17","author":"keisuke","year":"2009","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref4","first-page":"1","article-title":"The reverb challenge: A common evaluation framework for dereverberation and recognition of reverberant speech","author":"keisuke","year":"2013","journal-title":"2013 IEEE WASPAA IEEE"},{"key":"ref27","first-page":"55","article-title":"Speaker adaptation of neural network acoustic models using i-vectors","author":"george","year":"2013","journal-title":"ASRU"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1109\/MSP.2012.2205029","article-title":"Making machines understand us in reverberant rooms: Robustness against reverberation for automatic speech recognition","volume":"29","author":"takuya","year":"2012","journal-title":"IEEE Signal Processing Magazine"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1186\/s13634-015-0245-7","article-title":"Strategies for distant speech recognition in reverberant environments","volume":"2015","author":"marc","year":"2015","journal-title":"EURASIP Journal on Advances in Signal Processing"},{"key":"ref29","author":"francois","year":"2015","journal-title":"Keras Deep learning library for theano and tensorflow"},{"key":"ref5","author":"matthias","year":"2009","journal-title":"Distant Speech Recognition"},{"key":"ref8","first-page":"2751","article-title":"Purely sequence-trained neural networks for asr based on lattice-free MMI","author":"daniel","year":"2016","journal-title":"InterSpeech"},{"key":"ref7","article-title":"A time delay neural network architecture for efficient modeling of long temporal contexts","author":"vijayaditya","year":"2015","journal-title":"InterSpeech"},{"key":"ref2","article-title":"Low latency acoustic modeling using temporal convolution and LSTMs","author":"vijayaditya","year":"2017","journal-title":"IEEE Signal Processing Letters"},{"key":"ref9","first-page":"28","article-title":"The ami meeting corpus: A preannouncement","author":"jean","year":"2005","journal-title":"5th International Workshop on Machine Learning for Multimodal Interaction"},{"key":"ref1","first-page":"5755","article-title":"Highway long short-term memory rnns for distant speech recognition","author":"yu","year":"2016","journal-title":"ICASSP IEEE"},{"key":"ref20","article-title":"Reverberation robust acoustic modeling using i-vectors with time delay neural networks","author":"vijayaditya","year":"0","journal-title":"INTER-SPEECH 2015"},{"key":"ref22","first-page":"285","article-title":"Hy-brid acoustic models for distant and multichannel large vocabulary speech recognition","author":"pawel","year":"2013","journal-title":"ASRU IEEE"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1007\/s10579-007-9040-x","article-title":"Unleashing the killer corpus: experiences in creating the multi-everything ami meeting corpus","volume":"41","author":"jean","year":"2007","journal-title":"Language Resources and Evaluation"},{"key":"ref24","article-title":"The kaldi speech recognition toolkit","author":"daniel","year":"2011","journal-title":"IEEE ASRU IEEE Signal Processing Society"},{"key":"ref23","first-page":"6645","article-title":"Speech recognition with deep recurrent neural networks","author":"alex","year":"2013","journal-title":"ICASSP IEEE"},{"key":"ref26","article-title":"Audio augmentation for speech recognition","author":"tom","year":"2015","journal-title":"TERSPEECH"},{"key":"ref25","article-title":"Far-field asr without parallel data","author":"vijayaditya","year":"2016","journal-title":"Proceedings of Interspeech"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Calgary, AB","start":{"date-parts":[[2018,4,15]]},"end":{"date-parts":[[2018,4,20]]}},"container-title":["2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8450881\/8461260\/08461580.pdf?arnumber=8461580","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T22:38:07Z","timestamp":1598222287000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8461580\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8461580","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}