WFST-based Structured Classification of Features Extracted by Using Deep Neural Networks
Nakamura Atsushi , Kubo Yotaro , Hori Takaaki
IEICE technical report. Speech 112 ( 141) 39 -44
2012
Explicit Event Duration-Controlled BLSTM-HSMM Hybrid Model for Polyphonic Sound Event Detection
Toda Tomoki , Takeda Kazuya , Hayashi Tomoki , Roux JonathanLe
IEICE Technical Report; IEICE Tech. Rep. 117 ( 138) 9 -14
2017
Open-Vocabulary Spoken Utterance Retrieval Using Confusion Networks and Its Evaluation
Hori Takaaki , Glass James , Hazen Timothy , Hetherington Lee
IEICE Technical Report; IEICE Tech. Rep. 107 ( 356) 43 -48
2007
Streaming End-to-End Speech Recognition with Joint CTC-Attention Based Models
Hori Takaaki , Roux Jonathan Le , Moritz Niko
IEEE Conference Proceedings 2019 936 -943
36
2019
Efficient prior and incremental beam width control to suppress excessive speech recognition time based on score range estimation
Kobashikawa Satoshi , Hori Takaaki , Yamaguchi Yoshikazu , Asami Taichi
spoken language technology workshop 125 -130
2012
Advances in Multi-speaker Conversational Speech Recognition and Understanding
Hori Takaaki , Araki Shoko , Nakatani Tomohiro , Nakamura Atsushi
NTT Technical Review 11 ( 12) 10 -18
2013
Media Processing Technology for Business Task Support
Oba Takanobu , Kobayashi Kazunori , Uematsu Hisashi , Asami Taichi
NTT Technical Review 13 ( 4) 45 -51
2015
Speech Recognition Based on Unified Model of Acoustic and Language Aspects of Speech
Kubo Yotaro , Ogawa Atsunori , Hori Takaaki , Nakamura Atsushi
NTT Technical Review 11 ( 12) 19 -24
2013
CONSTRUCTION OF WEIGHTED FINITE STATE TRANSDUCERS FOR VERY WIDE CONTEXT-DEPENDENT ACOUSTIC MODELS
Mike Schuster Takaaki Hori
Improvements of search error risk minimization in viterbi beam search for speech recognition
Takaaki Hori , Shinji Watanabe , Atsushi Nakamura
conference of the international speech communication association 1962 -1965
2010
Efficient Discriminative Training of Error Corrective Models Using High-WER Competitors
Takaaki Hori , Takanobu Oba , Atsushi Nakamura
IEICE Technical Report; IEICE Tech. Rep. 38 ( 2) 135 -140
3
2008
Restructuring output layers of deep neural networks using minimum risk parameter clustering
Takaaki Hori , Yotaro Kubo , Atsushi Nakamura , Jun Suzuki
conference of the international speech communication association 1068 -1072
1
2014
Research on Meeting Analysis and Its Perspective
Takaaki Hori , Tomohiro Nakatani , Kazuhiro Otsuka , Junji Yamato
IEICE technical report. Speech 112 ( 141) 13 -18
2012
Multichannel end-to-end speech recognition
Takaaki Hori , John R. Hershey , Shinji Watanabe , Tsubasa Ochiai
international conference on machine learning 2632 -2641
38
2017
End-to-end Conversation Modeling Track in DSTC6
Takaaki Hori , Chiori Hori
arXiv: Computation and Language
42
2017
Cycle-consistency training for end-to-end speech recognition.
Takaaki Hori , Ramon Astudillo , Jonathan Le Roux , Shinji Watanabe
arXiv: Computation and Language
78
2018
Multi-encoder multi-resolution framework for end-to-end speech recognition
Hynek Hermansky , Takaaki Hori , Sri Harish Mallidi , Xiaofei Wang
arXiv: Computation and Language
11
2018
Multimodal Attention for Fusion of Audio and Spatiotemporal Features for Video Description
Takaaki Hori , Chiori Hori , Gordon Wichern , Teng-Yok Lee
computer vision and pattern recognition 2528 -2531
19
2018
End-to-end Speech Recognition with Word-based RNN Language Models
Takaaki Hori , Shinji Watanabe , Jaejin Cho
arXiv: Computation and Language
107
2018
Attention-Based Multimodal Fusion for Video Description
Chiori Hori , Takaaki Hori , Teng-Yok Lee , Ziming Zhang
arXiv: Computer Vision and Pattern Recognition
324
2017