HYB-VITON: A Hybrid Approach to Virtual Try-On Combining Explicit and Implicit Warping

Authors: Takemoto, Kosuke, Koshinaka, Takafumi

Subject Terms: Computer Science - Computer Vision and Pattern Recognition

Access URL: http://arxiv.org/abs/2501.03910

Reading Is Believing: Revisiting Language Bottleneck Models for Image Classification

Authors: Udo, Honori, Koshinaka, Takafumi

Subject Terms: Computer Science - Computer Vision and Pattern Recognition

Access URL: http://arxiv.org/abs/2406.15816

Generalized domain adaptation framework for parametric back-end in speaker recognition

Authors: Wang, Qiongqiong, Okabe, Koji, Lee, Kong Aik, Koshinaka, Takafumi

Subject Terms: Electrical Engineering and Systems Science - Audio and Speech Processing

Access URL: http://arxiv.org/abs/2305.15567

Image Captioners Sometimes Tell More Than Images They See

Authors: Udo, Honori, Koshinaka, Takafumi

Subject Terms: Computer Science - Computer Vision and Pattern Recognition, Computer Science - Multimedia

Access URL: http://arxiv.org/abs/2305.02932

Task-aware Warping Factors in Mask-based Speech Enhancement

Authors: Wang, Qiongqiong, Lee, Kong Aik, Koshinaka, Takafumi, Okabe, Koji, Yamamoto, Hitoshi

Source: 2021 29th European Signal Processing Conference (EUSIPCO) Signal Processing Conference (EUSIPCO), 2021 29th European. :476-480 Aug, 2021

Relation: 2021 29th European Signal Processing Conference (EUSIPCO)

A Generalized Framework for Domain Adaptation of PLDA in Speaker Recognition

Authors: Wang, Qiongqiong, Okabe, Koji, Lee, Kong Aik, Koshinaka, Takafumi

Source: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2020 - 2020 IEEE International Conference on. :6619-6623 May, 2020

Relation: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

The CORAL+ Algorithm for Unsupervised Domain Adaptation of PLDA

Authors: Lee, Kong Aik, Wang, Qiongqiong, Koshinaka, Takafumi

Source: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2019 - 2019 IEEE International Conference on. :5821-5825 May, 2019

Relation: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Xi-Vector Embedding for Speaker Recognition

Authors: Lee, Kong Aik, Wang, Qiongqiong, Koshinaka, Takafumi

Subject Terms: Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Sound

Access URL: http://arxiv.org/abs/2108.05679

Attention Mechanism in Speaker Recognition: What Does it Learn in Deep Speaker Embedding?

Authors: Wang, Qiongqiong, Okabe, Koji, Lee, Kong Aik, Yamamoto, Hitoshi, Koshinaka, Takafumi

Source: 2018 IEEE Spoken Language Technology Workshop (SLT) Spoken Language Technology Workshop (SLT), 2018 IEEE. :1052-1059 Dec, 2018

Relation: 2018 IEEE Spoken Language Technology Workshop (SLT)

Using Multi-Resolution Feature Maps with Convolutional Neural Networks for Anti-Spoofing in ASV

Authors: Wang, Qiongqiong, Lee, Kong Aik, Koshinaka, Takafumi

Subject Terms: Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Sound

Access URL: http://arxiv.org/abs/2008.08865

DNN Based Speaker Embedding Using Content Information for Text-Dependent Speaker Verification

Authors: Dey, Subhadeep, Koshinaka, Takafumi, Motlicek, Petr, Madikeri, Srikanth

Source: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Acoustics, Speech and Signal Processing (ICASSP), 2018 IEEE International Conference on. :5344-5348 Apr, 2018

Relation: ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Robust i-vector extraction tightly coupled with voice activity detection using deep neural networks

Authors: Yamamoto, Hitoshi, Okabe, Koji, Koshinaka, Takafumi

Source: 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2017. :600-604 Dec, 2017

Relation: 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)

Unleashing the Unused Potential of I-Vectors Enabled by GPU Acceleration

Authors: Vestman, Ville, Lee, Kong Aik, Kinnunen, Tomi H., Koshinaka, Takafumi

Subject Terms: Computer Science - Machine Learning, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing, Statistics - Machine Learning

Access URL: http://arxiv.org/abs/1906.08556

Fast and accurate personal authentication using ear acoustics

Authors: Arakawa, Takayuki, Koshinaka, Takafumi, Yano, Shohei, Irisawa, Hideki, Miyahara, Ryoji, Imaoka, Hitoshi

Source: 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA) Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2016 Asia-Pacific. :1-4 Dec, 2016

Relation: 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

Domain adaptation using maximum likelihood linear transformation for PLDA-based speaker verification

Authors: Wang, Qiongqiong, Yamamoto, Hitoshi, Koshinaka, Takafumi

Source: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Acoustics, Speech and Signal Processing (ICASSP), 2016 IEEE International Conference on. :5110-5114 Mar, 2016

Relation: ICASSP 2016 - 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

I4U Submission to NIST SRE 2018: Leveraging from a Decade of Shared Experiences

Authors: Lee, Kong Aik, Hautamaki, Ville, Kinnunen, Tomi, Yamamoto, Hitoshi, Okabe, Koji, Vestman, Ville, Huang, Jing, Ding, Guohong, Sun, Hanwu, Larcher, Anthony, Das, Rohan Kumar, Li, Haizhou, Rouvier, Mickael, Bousquet, Pierre-Michel, Rao, Wei, Wang, Qing, Zhang, Chunlei, Bahmaninezhad, Fahimeh, Delgado, Hector, Patino, Jose, Wang, Qiongqiong, Guo, Ling, Koshinaka, Takafumi, Zhang, Jiacen, Shinoda, Koichi, Trong, Trung Ngo, Sahidullah, Md, Lu, Fan, Tang, Yun, Tu, Ming, Teh, Kah Kuan, Tran, Huy Dat, George, Kuruvachan K., Kukanov, Ivan, Desnous, Florent, Yang, Jichen, Yilmaz, Emre, Xu, Longting, Bonastre, Jean-Francois, Xu, Chenglin, Lim, Zhi Hao, Chng, Eng Siong, Ranjan, Shivesh, Hansen, John H. L., Todisco, Massimiliano, Evans, Nicholas

Subject Terms: Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Computation and Language, Computer Science - Sound

Access URL: http://arxiv.org/abs/1904.07386

The CORAL+ Algorithm for Unsupervised Domain Adaptation of PLDA

Authors: Lee, Kong Aik, Wang, Qiongqiong, Koshinaka, Takafumi

Subject Terms: Computer Science - Machine Learning, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing, Statistics - Machine Learning

Access URL: http://arxiv.org/abs/1812.10260

Attentive Statistics Pooling for Deep Speaker Embedding

Authors: Okabe, Koji, Koshinaka, Takafumi, Shinoda, Koichi

Subject Terms: Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Sound

Access URL: http://arxiv.org/abs/1803.10963

Anomaly detection of motors with feature emphasis using only normal sounds

Authors: Ono, Yumi, Onishi, Yoshifumi, Koshinaka, Takafumi, Takata, Soichiro, Hoshuyama, Osamu

Source: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on. :2800-2804 May, 2013

Relation: ICASSP 2013 - 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

A noise-robust speech recognition method composed of weak noise suppression and weak Vector Taylor Series Adaptation

Authors: Komeiji, Shuji, Arakawa, Takayuki, Koshinaka, Takafumi

Source: 2012 IEEE Spoken Language Technology Workshop (SLT) Spoken Language Technology Workshop (SLT), 2012 IEEE. :103-106 Dec, 2012

Relation: 2012 IEEE Spoken Language Technology Workshop (SLT 2012)