Search

Search Funnelback University

Search powered by Funnelback
10 results 20 results 50 results
Relevance Date (Newest first) Date (Oldest first) Title (A-Z) Title (Z-A) Distance URL (A-Z) URL (Z-A) Shuffle
1 - 20 of 25 search results for TALK:ZA31 24 / |u:mi.eng.cam.ac.uk where 0 match all words and 25 match some words.

  1. Results that match 1 of 2 words

  2. Towards Learning Orientated Assessment for Non-native Learner Spoken…

    mi.eng.cam.ac.uk/~kmk/presentations/ALTA_Sheffield_20190306.pdf
    8 Mar 2019: 300 300. 25.5. 400 24.5. 400 24.4. ASR on Non-native Speech (2). • ... Thai dh d 7.24 oh aa 5.21. 30. • Top 2 recurrent substitution errors for speakers in each L1.

  3. LEARNING BETWEEN DIFFERENT TEACHER AND STUDENT MODELS IN ASR ...

    mi.eng.cam.ac.uk/~mjfg/ALTA/ASRU2019_TS.pdf
    20 Dec 2019: The derivatives of the per-frame. observation log-likelihoods with respects to the parameters are [24]. ... Work in [24] suggests several methods to improve gra-dient descent training of a GMM.

  4. BI-DIRECTIONAL LATTICE RECURRENT NEURAL NETWORKSFOR CONFIDENCE…

    mi.eng.cam.ac.uk/~ar527/ragni_icassp2019.pdf
    5 Feb 2019: may include embeddings [24], acoustic andlanguage model scores and other information. ... 24] T. Mikolov, I. Sutskever, K. Chen, S. S. Corrado, and J.

  5. Applying Deep Learning in Non-native Spoken English Assessment

    mi.eng.cam.ac.uk/~kmk/presentations/APSIPA2019_Knill_Keynote.pdf
    21 Nov 2019: 1.0 indicates within one CEFR grade-level. 24/45. Assessment System Performance. • ... 1.0 indicates within one CEFR grade-level. 24/45. Performance Analysis. 25/45.

  6. CONFIDENCE ESTIMATION AND DELETION PREDICTION USINGBIDIRECTIONAL…

    mi.eng.cam.ac.uk/~mjfg/ALTA/publications/SLT2018_ragni.pdf
    31 Aug 2019: Thesefeatures may include various statistics extracted from audio, acousticmodels, language models and lattices [24]. ... 24] T. Schaaf and T. Kemp, “Confidence measures for spontaneousspeech recognition,” in ICASSP, 1997.

  7. SEQUENCE TEACHER-STUDENT TRAINING OF ACOUSTIC MODELS FOR…

    mi.eng.cam.ac.uk/~mjfg/ALTA/publications/wang_slt18.pdf
    25 Feb 2019: It calculates the denominator by directly applying forward-backward computations [23, 24] on an unpruned denominator graphon GPU hardware. ... In Proc. ICASSP, volume 2,pages 605–608, 1996. [24] P. C. Woodland and D.

  8. BI-DIRECTIONAL LATTICE RECURRENT NEURAL NETWORKSFOR CONFIDENCE…

    mi.eng.cam.ac.uk/~mjfg/ALTA/publications/ICASSP2019_li.pdf
    31 Aug 2019: may include embeddings [24], acoustic andlanguage model scores and other information. ... 24] T. Mikolov, I. Sutskever, K. Chen, S. S. Corrado, and J.

  9. POUDEL, LIWICKI, CIPOLLA: FAST-SCNN: FAST SEGMENTATION NETWORK 1…

    mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2019-BMVC-Fast-SCNN.pdf
    12 Aug 2019: 1.1 ContributionsCurrently, semantic segmentation is typically addressed by a DCNN [2, 18, 24, 30]. ... arXiv:1801.04381 [cs], 2018. [24] E. Shelhamer, J. Long, and T. Darrell.

  10. IMPROVED AUTO-MARKING CONFIDENCE FOR SPOKEN LANGUAGE ASSESSMENT M.…

    mi.eng.cam.ac.uk/~mjfg/ALTA/publications/vecchio_slt18.pdf
    25 Feb 2019: AUCr =AUCmodel AUCradom. AUCoptimal AUCradom. (24). where AUCradom, AUCoptimal and AUCmodel represent thearea under the random, optimal and model back-off curvesrespectively.

  11. To appear Proc. ICASSP. c©2019 IEEE. Personal use of ...

    mi.eng.cam.ac.uk/~mjfg/ALTA/publications/Knill_ICASSP2019_AcceptedPaper.pdf
    3 Mar 2019: 24.3 23.6 21.0 25.2.

  12. CONVCRFS: CONVOLUTIONAL CRFS FOR SEMANTIC SEGMENTATION 1…

    mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2019-BMVC-Convolutional-CRF.pdf
    12 Aug 2019: The CNN is trained for 200 epochs using a batch size of 16 and the adam optimizer [16].The initial learning rate is set to 5105 and polynomially decreased [7, 24] ... Springer, 2014. [24] Wei Liu, Andrew Rabinovich, and Alexander C Berg.

  13. A Differential Volumetric Approach to Multi-View Photometric Stereo…

    mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2019-ICCV-Differential-MVPS.pdf
    12 Aug 2019: Additional realistic ef-fects such as ambient light ([24]) can also be included in theproposed model. ... 2. [24] Fotios Logothetis, Roberto Mecca, Yvain Quéau, andRoberto Cipolla. Near-field photometric stereo in ambientlight.

  14. POUDEL, LIWICKI, CIPOLLA: FAST-SCNN: FAST SEGMENTATION NETWORK 1…

    mi.eng.cam.ac.uk/~cipolla/archive/Publications/inproceedings/2019-BMVC-Fast-SCNN.pdf
    12 Aug 2019: 1.1 ContributionsCurrently, semantic segmentation is typically addressed by a DCNN [2, 18, 24, 30]. ... arXiv:1801.04381 [cs], 2018. [24] E. Shelhamer, J. Long, and T. Darrell.

  15. Creatures great and SMAL: Recovering theshape and motion of ...

    mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2018-ACCV-3D-animal-shape.pdf
    12 Aug 2019: The learning rate was decayedby 5% every 10k iterations. Training until convergence took 24 hours on a NvidiaTitan X GPU. ... In: Computer Vision and Pattern Regognition (CVPR). (2018). 24. Wiles, O., Zisserman, A.: Silnet : Single- and multi-view

  16. Orientation-Aware Semantic Segmentation on Icosahedron Spheres Chao…

    mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2019-ICCV-Segmentation-Icosahedron.pdf
    12 Aug 2019: pedestrian” and“cyclist”) which we attribute to unbalanced dataset. Futurework will incorporate better architectures such as [30, 24]for improved segmentation of small objects. ... In CVPR’16, pages 3234–3243, 2016. [24] Mark Sandler, Andrew

  17. SegNet: A Deep Convolutional Encoder-DecoderArchitecture for Image…

    mi.eng.cam.ac.uk/~cipolla/publications/article/2017-PAMI-SegNet.pdf
    11 Sep 2019: We conclude in Section 6. 2 LITERATURE REVIEW. Semantic pixel-wise segmentation is an active topic ofresearch, fuelled by challenging datasets [20], [21], [22], [24],[25]. ... In more recent work [24], both class segmentationand support relationships are

  18. Multi-Task Learning Using Uncertainty to Weigh Losses for Scene…

    mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2018-CVPR-multi-task-learning.pdf
    11 Sep 2019: toward feature space analysis. IEEE Transactions on pattern. analysis and machine intelligence, 24(5):603–619, 2002. ... ference on, pages 7304–7308. IEEE, 2013. 1. [24] A. Kendall and Y.

  19. CONVCRFS: CONVOLUTIONAL CRFS FOR SEMANTIC SEGMENTATION 1…

    mi.eng.cam.ac.uk/~cipolla/archive/Publications/inproceedings/2019-BMVC-Convolutional-CRF.pdf
    12 Aug 2019: The CNN is trained for 200 epochs using a batch size of 16 and the adam optimizer [16].The initial learning rate is set to 5105 and polynomially decreased [7, 24] ... Springer, 2014. [24] Wei Liu, Andrew Rabinovich, and Alexander C Berg.

  20. A Differential Volumetric Approach to Multi-View Photometric Stereo…

    mi.eng.cam.ac.uk/~cipolla/archive/Publications/inproceedings/2019-ICCV-Differential-MVPS.pdf
    12 Aug 2019: Additional realistic ef-fects such as ambient light ([24]) can also be included in theproposed model. ... 2. [24] Fotios Logothetis, Roberto Mecca, Yvain Quéau, andRoberto Cipolla. Near-field photometric stereo in ambientlight.

  21. Creatures great and SMAL: Recovering theshape and motion of ...

    mi.eng.cam.ac.uk/~cipolla/archive/Publications/inproceedings/2018-ACCV-3D-animal-shape.pdf
    12 Aug 2019: The learning rate was decayedby 5% every 10k iterations. Training until convergence took 24 hours on a NvidiaTitan X GPU. ... In: Computer Vision and Pattern Regognition (CVPR). (2018). 24. Wiles, O., Zisserman, A.: Silnet : Single- and multi-view

Refine your results

clear all

Date

Search history

Recently clicked results

Recently clicked results

Your click history is empty.

Recent searches

Recent searches

Your search history is empty.