@inproceedings{CTT100927130, author = {Roland Hartanto and Sakriani Sakti and Koichi Shinoda}, title = {MSDET: Multitask Speaker Separation and Direction-of-Arrival Estimation Training}, booktitle = {Proc. Interspeech 2024}, year = 2024, } @inproceedings{CTT100921185, author = {Roland Hartanto and Sakriani Sakti and Koichi Shinoda}, title = {Multitask Learning of Speaker Separation and Direction-of-Arrival Estimation}, booktitle = {日本音響学会第151回(2024年春季)研究発表会 講演論文集}, year = 2024, } @inproceedings{CTT100885102, author = {Ruoyue Shen and Nakamasa Inoue and Koichi Shinoda}, title = {Text-Guided Object Detector for Multi-modal Video Question Answering}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023}, year = 2023, } @inproceedings{CTT100884155, author = {Roland Hartanto and Kuniaki Uto and Koichi Shinoda}, title = {Lattice-Based Data Augmentation for Code-Switching Speech Recognition}, booktitle = {Proceedings of 2022 APSIPA Annual Summit and Conference}, year = 2022, } @inproceedings{CTT100866884, author = {Roland HARTANTO and Kuniaki UTO and Koichi SHINODA}, title = {Incorporating Acoustic and Textual Information for Language Modeling in Code-switching Speech Recognition}, booktitle = {IEICE Technical Report}, year = 2022, }