Publications

Found 29 results
Author Title Type [ Year(Asc)]
Filters: Author is Oriel Vinyals  [Clear All Filters]
2014
Vinyals, O., & Wegmann S. (2014).  Chasing the Metric: Smoothing Learning Algorithms for Keyword Detection.
Donahue, J., Jia Y., Vinyals O., Hoffman J., Zhang N., Tzeng E., et al. (2014).  DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition.
2013
Jia, Y., Vinyals O., & Darrell T. (2013).  On Compact Codes for Spatially Pooled Features.
Vinyals, O., & Morgan N. (2013).  Deep vs. Wide: Depth on a Budget for Robust Speech Recognition.
Vinyals, O., Jia Y., & Darrell T. (2013).  Why Size Matters: Feature Coding as Nystrom Sampling.
2012
Friedland, G., Janin A., Imseng D., Anguera X., Gottlieb L., Huijbregts M., et al. (2012).  The ICSI RT-09 Speaker Diarization System. IEEE Transactions on Audio. 20(2), 371-381.
Vinyals, O., Jia Y., Deng L., & Darrell T. (2012).  Learning with Recursive Perceptual Representations.
Anguera, X., Bozonnet S., Evans N., Fredouille C., Friedland G., & Vinyals O. (2012).  Speaker Diarization: A Review of Recent Research. IEEE Transactions on Audio. 20(2), 356-370.
2011
Vinyals, O., & Ravuri S. (2011).  Comparing Multilayer Perceptron to Deep Belief Network Tandem Features for Robust ASR.
Boakye, K., Vinyals O., & Friedland G. (2011).  Improved Overlapped Speech Handling for Speaker Diarization. 941-944.
2010
Vinyals, O., Friedland G., & Morgan N. (2010).  Discriminative Training for Hierarchical Clustering in Speaker Diarization. 2326-2329.
Vaquero, C.., Vinyals O., & Friedland G. (2010).  A Hybrid Approach to Online Speaker Diarization. 2642-2645.
Vinyals, O., Martin E., & Friedland G. (2010).  Multimodal Indoor Localization: An Audio-Wireless-Based Approach. 120-125.
Friedland, G., Vinyals O., & Darrell T. (2010).  Multimodal Location Estimation. 1245-1251.
Friedland, G., Vinyals O., & Darrell T. (2010).  Multimodal Location Estimation.
Martin, E., Vinyals O., Friedland G., & Bajcsy R.. (2010).  Precise Indoor Localization Using Smart Phones. 787-790.
Bozonnet, S., Evans N., Anguera X., Vinyals O., Friedland G., & Fredouille C. (2010).  System Output Combination for Improved Speaker Diarization. 2642-2645.
2009
Vinyals, O., Deng L., Yu D., & Acero A. (2009).  Discriminative Pronunciation Learning Using Phonetic Decoder and Minimum-Classification-Error Criterion. 4445-4448.
Friedland, G., Vinyals O., Huang Y., & Müller C. (2009).  Fusing Short Term and Long Term Features for Improved Speaker Diarization. 4077-4080.
Friedland, G., Vinyals O., Huang Y., & Müller C. (2009).  Prosodic and Other Long-Term Features for Speaker Diarization. IEEE Transactions on Audio. 17(5), 985-993.
2008
Vinyals, O., & Friedland G. (2008).  A Hardware-Independent Fast Logarithm Approximation with Adjustable Accuracy. 61-65.
Friedland, G., & Vinyals O. (2008).  Live Speaker Identification in Conversations. 1017-1018.
Vinyals, O., & Friedland G. (2008).  Live Speaker Identification in Meetings:.
Vinyals, O., & Friedland G. (2008).  Modulation Spectrogram Features for Speaker Diarization. Proceedings of the 9th Annual Conference of the International Speech Communication Association (Interspeech 2008). 630-633.
Boakye, K., Trueba-Hornero B.., Vinyals O., & Friedland G. (2008).  Overlapped Speech Detection for Improved Speaker Diarization in Multiparty Meetings. 4353-4356.

Pages