- Harsham, B.A., Watanabe, S., Esenther, A., Hershey, J.R., Le Roux, J., Luan, Y., Nikovski, D.N., Potluru, V.K., "Driver Prediction to Improve Interaction with In-Vehicle HMI", Workshop on DSP for In-Vehicle Systems and Safety (DSP), October 2015.
BibTeX TR2015-120 PDF- @inproceedings{Harsham2015oct,
- author = {Harsham, B.A. and Watanabe, S. and Esenther, A. and Hershey, J.R. and {Le Roux}, J. and Luan, Y. and Nikovski, D.N. and Potluru, V.K.},
- title = {{Driver Prediction to Improve Interaction with In-Vehicle HMI}},
- booktitle = {Workshop on DSP for In-Vehicle Systems and Safety (DSP)},
- year = 2015,
- month = oct,
- url = {https://www.merl.com/publications/TR2015-120}
- }
- Abdelaziz, A.H., Watanabe, S., Hershey, J.R., Vincent, E., Kolossa, D., "Uncertainty Propagation Through Deep Neural Networks", Interspeech, September 2015, vol. 1 or 5, pp. 3561.
BibTeX TR2015-098 PDF- @inproceedings{Abdelaziz2015sep,
- author = {Abdelaziz, A.H. and Watanabe, S. and Hershey, J.R. and Vincent, E. and Kolossa, D.},
- title = {{Uncertainty Propagation Through Deep Neural Networks}},
- booktitle = {Interspeech},
- year = 2015,
- volume = {1 or 5},
- pages = 3561,
- month = sep,
- isbn = {978-1-5108-1790-6},
- url = {https://www.merl.com/publications/TR2015-098}
- }
- Chen, Z., Watanabe, S., Erdogan, H., Hershey, J.R., "Speech Enhancement and Recognition Using Multi-Task Learning of Long Short-Term Memory Recurrent Neural Networks", Interspeech, September 2015, vol. 1 of 5, pp. 1278.
BibTeX TR2015-100 PDF- @inproceedings{Chen2015sep,
- author = {Chen, Z. and Watanabe, S. and Erdogan, H. and Hershey, J.R.},
- title = {{Speech Enhancement and Recognition Using Multi-Task Learning of Long Short-Term Memory Recurrent Neural Networks}},
- booktitle = {Interspeech},
- year = 2015,
- volume = {1 of 5},
- pages = 1278,
- month = sep,
- isbn = {978-1-5108-1790-6},
- url = {https://www.merl.com/publications/TR2015-100}
- }
- Luan, Y., Watanabe, S., Harsham, B.A., "Efficient Learning for Spoken Language Understanding Tasks with Word Embedding Based Pre-Training", Interspeech, September 2015, vol. 1 or 5, pp. 1398-1402.
BibTeX TR2015-097 PDF- @inproceedings{Luan2015sep,
- author = {Luan, Y. and Watanabe, S. and Harsham, B.A.},
- title = {{Efficient Learning for Spoken Language Understanding Tasks with Word Embedding Based Pre-Training}},
- booktitle = {Interspeech},
- year = 2015,
- volume = {1 or 5},
- pages = {1398--1402},
- month = sep,
- isbn = {978-1-5108-1790-6},
- url = {https://www.merl.com/publications/TR2015-097}
- }
- Tachioka, Y., Watanabe, S., "Uncertainty Training and Decoding Methods of Deep Neural Networks Based on Stochastic Representation of Enhanced Features", Interspeech, September 2015, vol. 1 or 5, pp. 3541.
BibTeX TR2015-099 PDF- @inproceedings{Tachioka2015sep,
- author = {Tachioka, Y. and Watanabe, S.},
- title = {{Uncertainty Training and Decoding Methods of Deep Neural Networks Based on Stochastic Representation of Enhanced Features}},
- booktitle = {Interspeech},
- year = 2015,
- volume = {1 or 5},
- pages = 3541,
- month = sep,
- isbn = {978-1-5108-1790-6},
- url = {https://www.merl.com/publications/TR2015-099}
- }
- Weninger, F.J., Erdogan, H., Watanabe, S., Vincent, E., Le Roux, J., Hershey, J.R., Schuller, B.W., "Speech Enhancement with LSTM Recurrent Neural Networks and Its Application to Noise-Robust ASR", Latent Variable Analysis and Signal Separation Conference (LVA), DOI: 10.1007/978-3-319-22482-4_11, August 2015, vol. 9237, pp. 91-99.
BibTeX TR2015-094 PDF- @inproceedings{Weninger2015aug,
- author = {Weninger, F.J. and Erdogan, H. and Watanabe, S. and Vincent, E. and {Le Roux}, J. and Hershey, J.R. and Schuller, B.W.},
- title = {{Speech Enhancement with LSTM Recurrent Neural Networks and Its Application to Noise-Robust ASR}},
- booktitle = {Latent Variable Analysis and Signal Separation Conference (LVA)},
- year = 2015,
- volume = 9237,
- pages = {91--99},
- month = aug,
- doi = {10.1007/978-3-319-22482-4_11},
- isbn = {978-3-319-22482-4},
- url = {https://www.merl.com/publications/TR2015-094}
- }
- Liu, M.-Y., Lin, A., Ramalingam, S., Tuzel, C.O., "Layered Interpretation of Street View Images", Robotics: Science and Systems Conference (RSS), DOI: 10.15607/RSS.2015.XI.025, July 2015.
BibTeX TR2015-073 PDF- @inproceedings{Liu2015jul,
- author = {Liu, M.-Y. and Lin, A. and Ramalingam, S. and Tuzel, C.O.},
- title = {{Layered Interpretation of Street View Images}},
- booktitle = {Robotics: Science and Systems Conference (RSS)},
- year = 2015,
- month = jul,
- doi = {10.15607/RSS.2015.XI.025},
- url = {https://www.merl.com/publications/TR2015-073}
- }
- Tachioka, Y., Narita, T., Watanabe, S., "Effectiveness of Dereverberation, Feature Transformation, Discriminative Training Methods, and System Combination Approach for Various Reverberant Environments", EURASIP Journal on Advances in Signal Processing, DOI: 10.1186/s13634-015-0241-y, June 2015.
BibTeX TR2015-152 PDF- @article{Tachioka2015jun,
- author = {Tachioka, Y. and Narita, T. and Watanabe, S.},
- title = {{Effectiveness of Dereverberation, Feature Transformation, Discriminative Training Methods, and System Combination Approach for Various Reverberant Environments}},
- journal = {EURASIP Journal on Advances in Signal Processing},
- year = 2015,
- month = jun,
- doi = {10.1186/s13634-015-0241-y},
- url = {https://www.merl.com/publications/TR2015-152}
- }
- Ahmed, E., Jones, M.J., Marks, T.K., "An Improved Deep Learning Architecture for Person Re-Identification", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), DOI: 10.1109/CVPR.2015.7299016, June 2015, pp. 3908-3916.
BibTeX TR2015-076 PDF- @inproceedings{Jones2015jun,
- author = {Ahmed, E. and Jones, M.J. and Marks, T.K.},
- title = {{An Improved Deep Learning Architecture for Person Re-Identification}},
- booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
- year = 2015,
- pages = {3908--3916},
- month = jun,
- doi = {10.1109/CVPR.2015.7299016},
- url = {https://www.merl.com/publications/TR2015-076}
- }
- Papazov, C., Marks, T.K., Jones, M.J., "Real-time Head Pose and Facial Landmark Estimation from Depth Images Using Triangular Surface Patch Features", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), DOI: 10.1109/CVPR.2015.7299104, June 2015, pp. 4722-4730.
BibTeX TR2015-069 PDF- @inproceedings{Marks2015jun,
- author = {Papazov, C. and Marks, T.K. and Jones, M.J.},
- title = {{Real-time Head Pose and Facial Landmark Estimation from Depth Images Using Triangular Surface Patch Features}},
- booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
- year = 2015,
- pages = {4722--4730},
- month = jun,
- publisher = {IEEE},
- doi = {10.1109/CVPR.2015.7299104},
- url = {https://www.merl.com/publications/TR2015-069}
- }
- Sharma, A., Tuzel, C.O., Jacobs, D., "Deep Hierarchical Parsing for Semantic Segmentation", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), DOI: 10.1109/CVPR.2015.7298651, June 2015, pp. 530-538.
BibTeX TR2015-057 PDF Video- @inproceedings{Sharma2015jun,
- author = {Sharma, A. and Tuzel, C.O. and Jacobs, D.},
- title = {{Deep Hierarchical Parsing for Semantic Segmentation}},
- booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
- year = 2015,
- pages = {530--538},
- month = jun,
- publisher = {IEEE},
- doi = {10.1109/CVPR.2015.7298651},
- issn = {1063-6919},
- url = {https://www.merl.com/publications/TR2015-057}
- }
- Erdogan, H., Hershey, J.R., Watanabe, S., Le Roux, J., "Phase-Sensitive and Recognition-Boosted Speech Separation Using Deep Recurrent Neural Networks", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2015.7178061, April 2015, pp. 708-712.
BibTeX TR2015-031 PDF- @inproceedings{Erdogan2015apr,
- author = {Erdogan, H. and Hershey, J.R. and Watanabe, S. and {Le Roux}, J.},
- title = {{Phase-Sensitive and Recognition-Boosted Speech Separation Using Deep Recurrent Neural Networks}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2015,
- pages = {708--712},
- month = apr,
- publisher = {IEEE},
- doi = {10.1109/ICASSP.2015.7178061},
- url = {https://www.merl.com/publications/TR2015-031}
- }
- Le Roux, J., Hershey, J.R., Weninger, F.J., "Deep NMF for Speech Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2015.7177933, April 2015, pp. 66-70.
BibTeX TR2015-029 PDF- @inproceedings{LeRoux2015apr1,
- author = {{Le Roux}, J. and Hershey, J.R. and Weninger, F.J.},
- title = {{Deep NMF for Speech Separation}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2015,
- pages = {66--70},
- month = apr,
- publisher = {IEEE},
- doi = {10.1109/ICASSP.2015.7177933},
- url = {https://www.merl.com/publications/TR2015-029}
- }
- Le Roux, J., Vincent, E., Hershey, J.R., Ellis, D.P.W., "Micbots: Collecting Large Realistic Datasets for Speech and Audio Research Using Mobile Robots", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2015.7179050, April 2015, pp. 5635-5639.
BibTeX TR2015-030 PDF- @inproceedings{LeRoux2015apr2,
- author = {{Le Roux}, J. and Vincent, E. and Hershey, J.R. and Ellis, D.P.W.},
- title = {{Micbots: Collecting Large Realistic Datasets for Speech and Audio Research Using Mobile Robots}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2015,
- pages = {5635--5639},
- month = apr,
- publisher = {IEEE},
- doi = {10.1109/ICASSP.2015.7179050},
- url = {https://www.merl.com/publications/TR2015-030}
- }
- Shinozaki, T., Watanabe, S., "Structure Discovery of Deep Neural Network Based on Evolutionary Algorithms", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2015.7178918, April 2015, pp. 4979-4983.
BibTeX TR2015-032 PDF- @inproceedings{Shinozaki2015apr,
- author = {Shinozaki, T. and Watanabe, S.},
- title = {{Structure Discovery of Deep Neural Network Based on Evolutionary Algorithms}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2015,
- pages = {4979--4983},
- month = apr,
- publisher = {IEEE},
- doi = {10.1109/ICASSP.2015.7178918},
- url = {https://www.merl.com/publications/TR2015-032}
- }
- Tachioka, Y., Watanabe, S., "Discriminative Method for Recurrent Neural Network Language Models", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2015.7179000, April 2015, pp. 5386-5390.
BibTeX TR2015-033 PDF- @inproceedings{Tachioka2015apr,
- author = {Tachioka, Y. and Watanabe, S.},
- title = {{Discriminative Method for Recurrent Neural Network Language Models}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2015,
- pages = {5386--5390},
- month = apr,
- publisher = {IEEE},
- doi = {10.1109/ICASSP.2015.7179000},
- url = {https://www.merl.com/publications/TR2015-033}
- }
- Le Roux, J., Weninger, F.J., Hershey, J.R., "Sparse NMF -- half-baked or well done?," Tech. Rep. TR2015-023, Mitsubishi Electric Research Laboratories, March 2015.
BibTeX TR2015-023 PDF- @techreport{LeRoux2015mar,
- author = {{Le Roux}, J. and Weninger, F.J. and Hershey, J.R.},
- title = {{Sparse NMF -- half-baked or well done?}},
- institution = {Mitsubishi Electric Research Laboratories},
- year = 2015,
- number = {TR2015-023},
- address = {Cambridge MA, USA},
- month = mar,
- url = {https://www.merl.com/publications/TR2015-023}
- }
- Gerkmann, T., Krawczyk, M., Le Roux, J., "Phase Processing for Single Channel Speech Enhancement: History and Recent Advances", IEEE Signal Processing Magazine, DOI: 10.1109/MSP.2014.2369251, Vol. 32, No. 2, pp. 55-66, March 2015.
BibTeX TR2014-122 PDF- @article{Gerkmann2015mar,
- author = {Gerkmann, T. and Krawczyk, M. and {Le Roux}, J.},
- title = {{Phase Processing for Single Channel Speech Enhancement: History and Recent Advances}},
- journal = {IEEE Signal Processing Magazine},
- year = 2015,
- volume = 32,
- number = 2,
- pages = {55--66},
- month = mar,
- publisher = {IEEE},
- doi = {10.1109/MSP.2014.2369251},
- issn = {1053-5888},
- url = {https://www.merl.com/publications/TR2014-122}
- }
- Weninger, F., Le Roux, J., Hershey, J.R., Schuller, B., "Discriminatively Trained Recurrent Neural Networks for Single-Channel Speech Separation", IEEE Global Conference on Signal and Information Processing (GlobalSIP), DOI: 10.1109/GlobalSIP.2014.7032183, December 2014, pp. 577-581.
BibTeX TR2014-104 PDF- @inproceedings{Weninger2014dec,
- author = {Weninger, F. and {Le Roux}, J. and Hershey, J.R. and Schuller, B.},
- title = {{Discriminatively Trained Recurrent Neural Networks for Single-Channel Speech Separation}},
- booktitle = {IEEE Global Conference on Signal and Information Processing (GlobalSIP)},
- year = 2014,
- pages = {577--581},
- month = dec,
- publisher = {IEEE},
- doi = {10.1109/GlobalSIP.2014.7032183},
- url = {https://www.merl.com/publications/TR2014-104}
- }
- Tachioka, Y., Watanabe, S., Le Roux, J., Hershey, J.R., "Sequential Maximum Mutual Information Linear Discriminant Analysis for Speech Recognition", Interspeech, September 2014, vol. 15, pp. 2415-2419.
BibTeX TR2014-079 PDF- @inproceedings{Tachioka2014sep,
- author = {Tachioka, Y. and Watanabe, S. and {Le Roux}, J. and Hershey, J.R.},
- title = {{Sequential Maximum Mutual Information Linear Discriminant Analysis for Speech Recognition}},
- booktitle = {Interspeech},
- year = 2014,
- volume = 15,
- pages = {2415--2419},
- month = sep,
- publisher = {International Speech Communication Association},
- issn = {2308-457X},
- url = {https://www.merl.com/publications/TR2014-079}
- }
- Watanabe, S., Hershey, J.R., Marks, T.K., Fujii, Y., Koji, Y., "Cost-level integration of statistical and rule-based dialog managers", Interspeech, September 2014, vol. 15, pp. 323-327.
BibTeX TR2014-082 PDF- @inproceedings{Watanabe2014sep,
- author = {{{Watanabe, S. and Hershey, J.R. and Marks, T.K. and Fujii, Y. and Koji, Y.}}},
- title = {{{Cost-level integration of statistical and rule-based dialog managers}}},
- booktitle = {Interspeech},
- year = 2014,
- volume = 15,
- pages = {323--327},
- month = sep,
- publisher = {International Speech Communication Association},
- url = {https://www.merl.com/publications/TR2014-082}
- }
- Weninger, F., Le Roux, J., Hershey, J.R., Watanabe, S., "Discriminative NMF and its application to single-channel source separation", Interspeech, September 2014, vol. 15, pp. 865-869.
BibTeX TR2014-081 PDF- @inproceedings{Weninger2014sep,
- author = {Weninger, F. and {Le Roux}, J. and Hershey, J.R. and Watanabe, S.},
- title = {{Discriminative NMF and its application to single-channel source separation}},
- booktitle = {Interspeech},
- year = 2014,
- volume = 15,
- pages = {865--869},
- month = sep,
- publisher = {International Speech Communication Association},
- issn = {2308-457X},
- url = {https://www.merl.com/publications/TR2014-081}
- }
- Le Roux, J., Vincent, E., "A Categorization of Robust Speech Processing Datasets," Tech. Rep. TR2014-116, Mitsubishi Electric Research Laboratories, September 2014.
BibTeX TR2014-116 PDF- @techreport{LeRouxVincent2014TRdatasets,
- author = {{Le Roux}, J. and Vincent, E.},
- title = {{A Categorization of Robust Speech Processing Datasets}},
- institution = {Mitsubishi Electric Research Laboratories},
- year = 2014,
- number = {TR2014-116},
- address = {Cambridge MA, USA},
- month = sep,
- note = {v2014-09},
- url = {https://www.merl.com/publications/TR2014-116}
- }
- Tuzel, O., Liu, M.-Y., Taguchi, Y., Raghunathan, A.U., "Learning to Rank 3D Features", European Conference on Computer Vision (ECCV), DOI: 10.1007/978-3-319-10590-1_34, September 2014, vol. 8689, pp. 520-535.
BibTeX TR2014-078 PDF- @inproceedings{Tuzel2014sep,
- author = {Tuzel, O. and Liu, M.-Y. and Taguchi, Y. and Raghunathan, A.U.},
- title = {{Learning to Rank 3D Features}},
- booktitle = {European Conference on Computer Vision (ECCV)},
- journal = {European Conference on Computer Vision (ECCV)},
- year = 2014,
- volume = 8689,
- series = {Lecture Notes in Computer Science},
- pages = {520--535},
- month = sep,
- doi = {10.1007/978-3-319-10590-1_34},
- issn = {0302-9743},
- isbn = {978-3-319-10589-5},
- url = {https://www.merl.com/publications/TR2014-078}
- }
- Hershey, J.R., Le Roux, J., Weninger, F., "Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures", arXiv, August 2014.
BibTeX arXiv- @article{Hershey2014aug,
- author = {Hershey, J.R. and {Le Roux}, J. and Weninger, F.},
- title = {{Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures}},
- journal = {arXiv},
- year = 2014,
- month = aug,
- url = {https://arxiv.org/abs/1409.2574}
- }