IEICE Technical Report

Online edition: ISSN 2432-6380

Natural Language Understanding and Models of Communication

Workshop Date : 2022-11-29 - 2022-12-01 / Issue Date : 2022-11-22

NLC2022-9
Link Prediction from Text Content by NLP Graph Embedding -- A Study on Chinese Journal Articles --
Tzu-Ying Yang, Hsuan Lei Shao, Chih-Chuan Fan, Wei-Hsin Wang (NTNU)
pp. 1 - 4

NLC2022-10
Density Ratio Approach-based multiple Encoder-Decoder ASR model integration
Keigo Hojo, Daiki Mori, Yukoh Wakabayashi (TUT), Atsunori Ogawa (NTT), Norihide Kitaoka (TUT)
pp. 5 - 9

NLC2022-11
Detecting Persona Information in Chat using Subject Recovery with Machine Translation
Shinji Muraji, Toshihiko Ito, Kenji Araki (Hokkaido Univ.)
pp. 10 - 15

NLC2022-12
Handling time information for matching broadcast metadata with user-generated text
Takeshi S. Kobayakawa (NHK), Takeshi Sakaki, Masanao Ochi, Sakata Ichiro (Univ. Tokyo)
pp. 16 - 20

NLC2022-13
Dialogue disfluency detection using context
Hiroto Nakashima, Kazutaka Shimada (KIT)
pp. 21 - 26

NLC2022-14
Semi-supervised joint training of text to speech and automatic speech recognition using unpaired text data
Naoki Makishima, Satoshi Suzuki, Atsushi Ando, Ryo Masumura (NTT)
pp. 27 - 32

NLC2022-15
Representing how it is said with what is said -- Creation and analysis of an English corpus of focused speech and text reflecting paralinguistically expressed implications --
Naoaki Suzuki, Satoshi Nakamura (NAIST)
pp. 33 - 38

NLC2022-16
A Japanese Automatic Speech Recognition System on the Next-Gen Kaldi Framework
Wen Shen Teo, Yasuhiro Minami (UEC)
pp. 39 - 44

NLC2022-17
Domain and language adaptation of large-scale pretrained model for speech recognition of low-resource language
Kak Soky (Kyoto University), Sheng Li (NICT), Chenhui Chu, Tatsuya Kawahara (Kyoto University)
pp. 45 - 49

NLC2022-18
ASR model adaptation to target domain with large-scale audio data without transcription
Takahiro Kinouchi, Daiki Mori (TUT), Ogawa Atsunori (NTT), Norihide Kitaoka (TUT)
pp. 50 - 53

Note: Each article is a technical report without peer review, and its polished version will be published elsewhere.

The Institute of Electronics, Information and Communication Engineers (IEICE), Japan