842 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Sony Corporation (United States)US3 papers
- Sony (Taiwan)TW3 papers
- Carnegie Mellon UniversityUS2 papers
- Sony Computer Science LaboratoriesJP2 papers
- University of California, BerkeleyUS2 papers
- University of Illinois Urbana-ChampaignUS2 papers
- University of SouthamptonGB2 papers
- Cybernet SYSTEMS Co., Ltd. (Japan)JP1 paper
- Dexerials (Japan)JP1 paper
- ETH ZurichCH1 paper
- European Space AgencyFR1 paper
- European Space Astronomy CentreES1 paper
22 papers
AI-driven Optimisation of Quality of Recovery (QoR) in Remote Patient Monitoring
Yansong Liu, Li-Hsi, Lin +4
Remote patient monitoring depends on patient-reported data to capture the subjective dimension of recovery that devices cannot measure. The Quality of Recovery (QoR-15) survey is t…
MixtureVitae: Open Web-Scale Pretraining Dataset With High Quality Instruction and Reasoning Data Built from Permissive-First Text Sources
Huu Nguyen, Victor May, Harsh Raj +14
We present MixtureVitae, an open-access pretraining corpus built to minimize legal risk while providing strong downstream performance. MixtureVitae follows a permissive-first, risk…
Biomarker Integration and Biosensor Technologies Enabling AI-Driven Insights into Biological Aging
Jared A Kushner, Mohit Pandey, Sandeep +1
As the global population continues to age, there is an increasing demand for ways to accurately quantify the biological processes underlying aging. Biological age, unlike chronolog…
Streaming Transformer ASR with Blockwise Synchronous Beam Search
Emiru Tsunoo, Yosuke Kashiwagi, Shinji Watanabe
The Transformer self-attention network has shown promising performance as an alternative to recurrent neural networks in end-to-end (E2E) automatic speech recognition (ASR) systems…
Iteratively Training Look-Up Tables for Network Quantization
Fabien Cardinaux, Stefan Uhlich, Kazuki Yoshiyama +5
Operating deep neural networks (DNNs) on devices with limited resources requires the reduction of their memory as well as computational footprint. Popular reduction methods are net…
Improving Voice Separation by Incorporating End-to-end Speech Recognition
Naoya Takahashi, Mayank Kumar Singh, Sakya Basak +3
Despite recent advances in voice separation methods, many challenges remain in realistic scenarios such as noisy recording and the limits of available data. In this work, we propos…
Nested Named Entity Recognition via Second-best Sequence Learning and Decoding
Takashi Shibuya, Eduard Hovy
When an entity name contains other names within it, the identification of all combinations of names can become difficult and expensive. We propose a new method to recognize not onl…
Context-Aware Dialog Re-Ranking for Task-Oriented Dialog Systems
Junki Ohmura, Maxine Eskenazi
Dialog response ranking is used to rank response candidates by considering their relation to the dialog history. Although researchers have addressed this concept for open-domain di…
MMDenseLSTM: An efficient combination of convolutional and recurrent neural networks for audio source separation
Naoya Takahashi, Nabarun Goswami, Yuki Mitsufuji
Deep neural networks have become an indispensable technique for audio source separation (ASS). It was recently reported that a variant of CNN architecture called MMDenseNet was suc…
Automatic Pronunciation Generation by Utilizing a Semi-supervised Deep Neural Networks
Naoya Takahashi, Tofigh Naghibi, Beat Pfister
Phonemic or phonetic sub-word units are the most commonly used atomic elements to represent speech signals in modern ASRs. However they are not the optimal choice due to several re…
Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding
Akira Fukui, Dong Huk Park, Daylen Yang +3
Modeling textual or visual information with vector representations trained from large language or visual datasets has been successfully explored in recent years. However, tasks suc…
Deep Convolutional Neural Networks and Data Augmentation for Acoustic Event Detection
Naoya Takahashi, Michael Gygli, Beat Pfister +1
We propose a novel method for Acoustic Event Detection (AED). In contrast to speech, sounds coming from acoustic events may be produced by a wide variety of sources. Furthermore, d…
Spatial Phase-Sweep: Increasing temporal resolution of transient imaging using a light source array
Ryuichi Tadano, Adithya Kumar Pediredla, Kaushik Mitra +1
Transient imaging or light-in-flight techniques capture the propagation of an ultra-short pulse of light through a scene, which in effect captures the optical impulse response of t…
On the symmetrical Kullback-Leibler Jeffreys centroids
Frank Nielsen
Due to the success of the bag-of-word modeling paradigm, clustering histograms has become an important ingredient of modern information processing. Clustering histograms can be per…
Chernoff information of exponential families
Frank Nielsen
Chernoff information upper bounds the probability of error of the optimal Bayesian decision rule for -class classification problems. However, it turns out that in practice the C…
A combinatorial approach to metamaterials discovery
E. Plum, K. Tanaka, W. T. Chen +3
We report a high through-put combinatorial approach to photonic metamaterial optimization. The new approach is based on parallel synthesis and consecutive optical characterization…
Multi-fold Enhancement of Quantum Dot Luminescence in a Plasmonic Metamaterial
K. Tanaka, E. Plum, J. Y. Ou +2
We report that hybridizing semiconductor quantum dots with plasmonic metamaterial leads to a multi-fold intensity increase and narrowing of their photoluminescence spectrum. The lu…
The distribution of first-passage times and durations in FOREX and future markets
Naoya Sazuka, Jun-ichi Inoue, Enrico Scalas
Possible distributions are discussed for intertrade durations and first-passage processes in financial markets. The view-point of renewal theory is assumed. In order to represent m…
The Infrared Astronomical Mission AKARI
H. Murakami, H. Baba, P. Barthel +90
AKARI, the first Japanese satellite dedicated to infrared astronomy, was launched on 2006 February 21, and started observations in May of the same year. AKARI has a 68.5 cm cooled…
Analysis of Binarized High Frequency Financial Data
Naoya Sazuka
A non-trivial probability structure is evident in the binary data extracted from the up/down price movements of very high frequency data such as tick-by-tick data for USD/JPY. In t…
Electronic mean free path in as-produced and purified single-wall carbon nanotubes
H. Kajiura, A. Nandyala, U. C. Coskun +3
The effect of purification on room temperature electronic transport properties of single-wall carbon nanotubes (SWNT) was studied by submerging samples into liquid mercury. The con…
Quasi-ballistic electron transport in double-wall carbon nanotubes
Hisashi Kajiura, Houjin Huang, Alexey Bezryadin
Room-temperature quasi-ballistic electron transport in double-wall carbon nanotubes (DWNT) is demonstrated. Conductance dependence on the length was measured by submerging DWNTs in…