Author of the publication

Knowledge Distillation Using Soft and Hard Labels and Annealing for Acoustic Model Training.

. GCCE, page 689-690. IEEE, (2019)

Please choose a person to relate this publication to

To differ between persons with the same name, the academic degree and the title of an important publication will be displayed. You can also use the button next to the name to display some publications already assigned to the person.

No persons found for author name Tachioka, Yuuki
add a person with the name Tachioka, Yuuki
 

Other publications of authors with the same name

Hypothesis Correction Based on Semi-character Recurrent Neural Network for End-to-end Speech Recognition.. APSIPA, page 862-867. IEEE, (2019)Feature-space structural MAPLR with regression tree-based multiple transformation matrices for DNN., , , and . APSIPA, page 86-92. IEEE, (2015)Privacy Preserving Acoustic Model Training for Speech Recognition.. APSIPA, page 627-631. IEEE, (2020)Uncertainty training and decoding methods of deep neural networks based on stochastic representation of enhanced features., and . INTERSPEECH, page 3541-3545. ISCA, (2015)Discriminative method for recurrent neural network language models., and . ICASSP, page 5386-5390. IEEE, (2015)Objective Measurement of the Relationship between Variants in Classical Literature.. Culture and Computing, page 202-203. IEEE Computer Society, (2013)Multi-channel Non-negative Matrix Factorization Initialized with Full-rank and Rank-1 Spatial Correlation Matrix for Speech Recognition.. ISPACS, page 246-251. IEEE, (2018)Integration of Annotator-wise Estimations for Emotion Recognition by Using Group Softmax.. APSIPA ASC, page 694-699. IEEE, (2021)Coupled Initialization of Multi-Channel Non-Negative Matrix Factorization Based on Spatial and Spectral Information., , , , , , , , and . INTERSPEECH, page 2461-2465. ISCA, (2017)Multilingual acoustic model training based on phoneme set conversion.. GCCE, page 921-922. IEEE, (2020)