Search Results - "Hori, Chiori"

Attention-Based Multimodal Fusion for Video Description by Hori, Chiori, Hori, Takaaki, Teng-Yok Lee, Ziming Zhang, Harsham, Bret, Hershey, John R., Marks, Tim K., Sumi, Kazuhiko

“…Current methods for video description are based on encoder-decoder sentence generation using recurrent neural networks (RNNs). Recent work has demonstrated the…”
Get full text

End-to-end Audio Visual Scene-aware Dialog Using Multimodal Attention-based Video Features by Hori, Chiori, Alamri, Huda, Wang, Jue, Wichern, Gordon, Hori, Takaaki, Cherian, Anoop, Marks, Tim K., Cartillier, Vincent, Lopes, Raphael Gontijo, Das, Abhishek, Essa, Irfan, Batra, Dhruv, Parikh, Devi

“…In order for machines interacting with the real world to have conversations with users about the objects and events around them, they need to understand…”
Get full text

Overview of the sixth dialog system technology challenge: DSTC6 by Hori, Chiori, Perez, Julien, Higashinaka, Ryuichiro, Hori, Takaaki, Boureau, Y-Lan, Inaba, Michimasa, Tsunomori, Yuiko, Takahashi, Tetsuro, Yoshino, Koichiro, Kim, Seokhwan

“…•DSTC6: Dialog Challenge to improve performance of end-to-end dialog systems using Neural Network models and dialog breakdown detection.•Track 1, End-to-End…”
Get full text

Sparse representation based on a bag of spectral exemplars for acoustic event detection by Xugang Lu, Yu Tsao, Matsuda, Shigeki, Hori, Chiori

“…Acoustic event detection is an important step for audio content analysis and retrieval. Traditional detection techniques model the acoustic events on…”
Get full text

Minimum word error training of long short-term memory recurrent neural network language models for speech recognition by Hori, Takaaki, Hori, Chiori, Watanabe, Shinji, Hershey, John R.

“…This paper describes minimum word error (MWE) training of recurrent neural network language models (RNNLMs) for speech recognition. RNNLMs are usually trained…”
Get full text

A-STAR: Toward translating Asian spoken languages by Sakti, Sakriani, Paul, Michael, Finch, Andrew, Sakai, Shinsuke, Vu, Thang Tat, Kimura, Noriyuki, Hori, Chiori, Sumita, Eiichiro, Nakamura, Satoshi, Park, Jun, Wutiwiwatchai, Chai, Xu, Bo, Riza, Hammam, Arora, Karunesh, Luong, Chi Mai, Li, Haizhou

“…► The first Asian network-based speech-to-speech translation system developed by the A-STAR consortium. ► A-STAR field testing experiments was carried out in…”
Get full text

Multilingual Speech-to-Speech Translation System: VoiceTra by Matsuda, Shigeki, Xinhui Hu, Shiga, Yoshinori, Kashioka, Hideki, Hori, Chiori, Yasuda, Keiji, Okuma, Hideo, Uchiyama, Masao, Sumita, Eiichiro, Kawai, Hisashi, Nakamura, Satoshi

“…This study presents an overview of VoiceTra, which was developed by NICT and released as the world's first network-based multilingual speech-to-speech…”
Get full text

Audio Visual Scene-Aware Dialog by Alamri, Huda, Cartillier, Vincent, Das, Abhishek, Wang, Jue, Cherian, Anoop, Essa, Irfan, Batra, Dhruv, Marks, Tim K., Hori, Chiori, Anderson, Peter, Lee, Stefan, Parikh, Devi

“…We introduce the task of scene-aware dialog. Our goal is to generate a complete and natural response to a question about a scene, given video and audio of the…”
Get full text

Early and late integration of audio features for automatic video description by Chiori Hori, Hori, Takaaki, Marks, Tim K., Hershey, John R.

“…This paper presents our approach to improve video captioning by integrating audio and video features. Video captioning is the task of generating a textual…”
Get full text

Automatic evaluation of end-to-end dialog systems with adequacy-fluency metrics by D'Haro, Luis Fernando, Banchs, Rafael E., Hori, Chiori, Li, Haizhou

“…•Automatic metric for evaluating natural language generated sentences for dialog systems.•Integration of adequacy and fluency information to jointly evaluate…”
Get full text

NIIRF: Neural IIR Filter Field for HRTF Upsampling and Personalization by Masuyama, Yoshiki, Wichern, Gordon, Germain, Francois G., Pan, Zexu, Khurana, Sameer, Hori, Chiori, Le Roux, Jonathan

“…Head-related transfer functions (HRTFs) are important for immersive audio, and their spatial interpolation has been studied to upsample finite measurements…”
Get full text

Generation or Replication: Auscultating Audio Latent Diffusion Models by Bralios, Dimitrios, Wichern, Gordon, Germain, Francois G., Pan, Zexu, Khurana, Sameer, Hori, Chiori, Roux, Jonathan Le

“…The introduction of audio latent diffusion models possessing the ability to generate realistic sound clips on demand from a text description has the potential…”
Get full text

WI-FI based Indoor Monitoring Enhanced by Multimodal Fusion by Hori, Chiori, Wang, Pu, Rahman, Mahbub, Vaca-Rubio, Cristian, Khurana, Sameer, Cherian, Anoop, Le Roux, Jonathan

“…Indoor monitoring systems are in high demand to protect vulnerable people, especially when they are alone at home, in nursing homes, hospitals, etc. Although…”
Get full text

Overview of the seventh Dialog System Technology Challenge: DSTC7 by D’Haro, Luis Fernando, Yoshino, Koichiro, Hori, Chiori, Marks, Tim K., Polymenakos, Lazaros, Kummerfeld, Jonathan K., Galley, Michel, Gao, Xiang

“…•DSTC7: Dialog Challenge to build more robust and accurate end-to-end dialog systems.•Track 1, Sentence selection for multiple domains, including variations…”
Get full text

Spatio-Temporal Ranked-Attention Networks for Video Captioning by Cherian, Anoop, Wang, Jue, Hori, Chiori, Marks, Tim K.

“…Generating video descriptions automatically is a challenging task that involves a complex interplay between spatio-temporal visual features and language…”
Get full text

Adversarial training and decoding strategies for end-to-end neural conversation models by Hori, Takaaki, Wang, Wen, Koji, Yusuke, Hori, Chiori, Harsham, Bret, Hershey, John R.

“…•An advanced end to end conversation system for the 6-th edition of Dialog System Technology Challenge (DSTC6).•Applying sequence adversarial training with…”
Get full text

Leveraging social Q&A collections for improving complex question answering by Wu, Youzheng, Hori, Chiori, Kashioka, Hideki, Kawai, Hisashi

“…•The proposed approach leverages social Q&A collections to improve automatic complex QA system.•There is no need to manually collect training Q&A pairs that…”
Get full text

A cloud robotics approach towards dialogue-oriented robot speech by Sugiura, Komei, Shiga, Yoshinori, Kawai, Hisashi, Misu, Teruhisa, Hori, Chiori

“…Robot utterances generally sound monotonous, unnatural and unfriendly because their Text-to-Speech systems are not optimized for communication but for text…”
Get full text

Superpositional HMM-Based Intonation Synthesis Using a Functional F0 Model by Ni, Jinfu, Shiga, Yoshinori, Hori, Chiori

“…This paper addresses intonation synthesis combining both statistical and generative models to manipulate fundamental frequency ( F 0 ) contours in the…”
Get full text

Efficient WFST-Based One-Pass Decoding With On-The-Fly Hypothesis Rescoring in Extremely Large Vocabulary Continuous Speech Recognition by Hori, T., Hori, C., Minami, Y., Nakamura, A.

“…This paper proposes a novel one-pass search algorithm with on-the-fly composition of weighted finite-state transducers (WFSTs) for large-vocabulary…”
Get full text