Publications - LY Corporation R&D

CONFERENCE (DOMESTIC)
CTC を用いた音声認識のための中間層予測による条件づけ: 野崎樹文 (京都大学), 小松達也; 日本音響学会 2021年秋季研究発表会 (ASJ 2021 autumn); September 07, 2021

CONFERENCE (DOMESTIC)
テキスト音声合成のための CycleGAN 声質変換を用いたデータ拡張の検討: 寺島涼, 山本龍一, 橘健太郎; 日本音響学会 2021年秋季研究発表会 (ASJ 2021 autumn); September 07, 2021

CONFERENCE (DOMESTIC)
音声意味理解への応用を指向した非自己回帰型End-to-end音声認識: 大町基, 藤田悠哉, 渡部晋治 (Carnegie Mellon University), Tianzi Wang (Johns Hopkins University); 日本音響学会　2021年秋季研究発表会 (音響学会); September 07, 2021

WORKSHOP (DOMESTIC)
Capturing spatial distribution of people interests with web queries and location data: A large scale empirical study of metropolises in Japan: Jinyuan Li (Tokyo Institute of Technology), Soto Anno (Tokyo Institute of Technology), Takayuki Sakamoto (Nikken Sekkei Ltd.), Hiraki Yasuda (Nikken Sekkei Ltd.), Akira Tsujimoto (Nikken Sekkei Ltd.), Kota Tsubouchi, Masamichi Shimosaka (Tokyo Institute of Technology); 情報処理学会第71回ユビキタスコンピューティングシステム (UBI) 研究発表会 (IPSJ SIGUBI); September 03, 2021

CONFERENCE (INTERNATIONAL)
Streaming End-to-End ASR based on Blockwise Non-Autoregressive Models: Tianzi Wang (Johns Hopkins University), Yuya Fujita, Xuankai Chang (Carnegie Mellon Univ.), Shinji Watanabe (Carnegie Mellon University); INTERSPEECH 2021; September 02, 2021

CONFERENCE (INTERNATIONAL)
Toward Streaming ASR with Non-Autoregressive Insertion-based Model: Yuya Fujita, Tianzi Wang (Johns Hopkins University), Shinji Watanabe (Carnegie Mellon University), Motoi Omach; INTERSPEECH 2021; September 02, 2021

OTHERS (DOMESTIC)
日本語版GLUE構築に向けて: 栗原健太郎 (早大), 河原大輔 (早大), 柴田知秀; NLP若手の会 (YANS) 第16回シンポジウム (YANS2021); August 31, 2021

CONFERENCE (INTERNATIONAL)
Acoustic Event Detection with Classifier Chains: Tatsuya Komatsu, Shinji Watanabe (Carnegie Mellon University), Koichi Miyazaki (Nagoya University), Tomoki Hayashi (Human Dataware Lab.); The 22nd Annual Conference of the International Speech Communication Association (INTERSPEECH 2021); August 30, 2021

CONFERENCE (INTERNATIONAL)
Comparing Performance Models for Bivariate Pointing through a Crowdsourced Experiment: Shota Yamanaka; INTERACT 2021; August 30, 2021

CONFERENCE (INTERNATIONAL)
Efficient and Stable Adversarial Learning Using Unpaired Data for Unsupervised Multichannel Speech Separation: Yu Nakagome (Waseda University), Masahito Togami, Tetsuji Ogawa (Waseda University), Tetsunori Kobayashi (Waseda University); The 22nd Annual Conference of the International Speech Communication Association (INTERSPEECH 2021); August 30, 2021

CONFERENCE (INTERNATIONAL)
High-fidelity Parallel WaveGAN with Multi-band Harmonic-plus-Noise Model: Min-Jae Hwang (Search Solutions Inc), Ryuichi Yamamoto, Eunwoo Song (NAVER), Jae-Min Kim (NAVER); The 22nd Annual Conference of the International Speech Communication Association (INTERSPEECH 2021); August 30, 2021

CONFERENCE (INTERNATIONAL)
Phrase break prediction with bidirectional encoder representations in Japanese text-to-speech synthesis: Kosuke Futamata, Byeongseon Park, Ryuichi Yamamoto, Kentaro Tachibana; The 22nd Annual Conference of the International Speech Communication Association (INTERSPEECH 2021); August 30, 2021

CONFERENCE (INTERNATIONAL)
Relaxing the Conditional Independence Assumption of CTC-based ASR by Conditioning on Intermediate Predictions: Jumon Nozaki (Kyoto University), Tatsuya Komatsu; The 22nd Annual Conference of the International Speech Communication Association (INTERSPEECH 2021); August 30, 2021

CONFERENCE (INTERNATIONAL)
Sound Source Localization with Majorization Minimization: Masahito Togami, Robin Scheilbler; The 22nd Annual Conference of the International Speech Communication Association (INTERSPEECH 2021); August 30, 2021

CONFERENCE (INTERNATIONAL)
Speech Representation Learning Combining Conformer CPC with Deep Cluster for the ZeroSpeech Challenge 2021: Takashi Maekaku, Xuankai Chang (Carnegie Mellon University), Yuya Fujita, Li, Shinji Watanabe (Carnegie Mellon University), Alexander Rudnicky (Carnegie Mellon University); INTERSPEECH 2021; August 30, 2021

CONFERENCE (INTERNATIONAL)
Time-Penalty Impact on Effective Index of Difficulty and Throughputs in Pointing Tasks: Shota Yamanaka, Keisuke Yokota (Meiji University), Takanori Komatsu (Meiji University); INTERACT 2021; August 30, 2021

CONFERENCE (INTERNATIONAL)
Multi-Source Domain Adaptation with Sinkhorn Barycenter: Tatsuya Komatsu, Tomoko Matsui (The Institute of Statistical Mathematics), Junbin Gao (The University of Sydney); 29th European Signal Processing Conference (EUSIPCO 2021); August 23, 2021

CONFERENCE (INTERNATIONAL)
Multichannel Separation and Classification of Sound Events: Robin Scheilbler, Tatsuya Komatsu, Masahito Togami; 29th European Signal Processing Conference (EUSIPCO 2021); August 23, 2021

CONFERENCE (DOMESTIC)
角膜反射を利用したスマートフォンの把持姿勢推定: 張翔 (慶應義塾大学), 池松香, 加藤邦拓 (東京工科大学), 杉浦裕太 (慶應義塾大学); エンタテインメントコンピューティングシンポジウム 2021 (EC2021); August 23, 2021

CONFERENCE (INTERNATIONAL)
Designing a persistent-memory-native storage engine for SQL database systems: Shohei Matsuura; The 10th IEEE Non-Volatile Memory Systems and Applications Symposium (IEEE NVMSA 2021); August 19, 2021