788 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Kyoto UniversityJP5 papers
- Naver (South Korea)KR5 papers
- Johns Hopkins UniversityUS3 papers
- Nagoya UniversityJP3 papers
- Waseda UniversityJP3 papers
- Carnegie Mellon UniversityUS2 papers
- Hitachi (Japan)JP2 papers
- NTT (Japan)JP2 papers
- Space Solutions (South Korea)KR2 papers
- Tokyo Metropolitan UniversityJP2 papers
- Doshisha UniversityJP1 paper
- École Polytechnique Fédérale de LausanneCH1 paper
26 papers
3-Key-Input: Exploring the Theoretical Minimum Keys for Text Entry
Naoki Kimura
How far can we reduce the number of physical keys if we endow an ambiguous keyboard with modern language models? Fewer keys increase hardware design freedom in constrained settings…
Congestion Forecast for Trains with Railroad-Graph-based Semi-Supervised Learning using Sparse Passenger Reports
Soto Anno, Kota Tsubouchi, Masamichi Shimosaka
Forecasting rail congestion is crucial for efficient mobility in transport systems. We present rail congestion forecasting using reports from passengers collected through a transit…
Network Shuffling: Privacy Amplification via Random Walks
Seng Pei Liew, Tsubasa Takahashi, Shun Takagi +3
Recently, it is shown that shuffling can amplify the central differential privacy guarantees of data randomized with local differential privacy. Within this setup, a centralized, t…
Alternate Intermediate Conditioning with Syllable-level and Character-level Targets for Japanese ASR
Yusuke Fujita, Tatsuya Komatsu, Yusuke Kida
End-to-end automatic speech recognition directly maps input speech to characters. However, the mapping can be problematic when several different pronunciations should be mapped int…
HDPView: Differentially Private Materialized View for Exploring High Dimensional Relational Data
Fumiyuki Kato, Tsubasa Takahashi, Shun Takagi +3
How can we explore the unknown properties of high-dimensional sensitive relational data while preserving privacy? We study how to construct an explorable privacy-preserving materia…
Acoustic Event Detection with Classifier Chains
Tatsuya Komatsu, Shinji Watanabe, Koichi Miyazaki +1
This paper proposes acoustic event detection (AED) with classifier chains, a new classifier based on the probabilistic chain rule. The proposed AED with classifier chains consists…
Unified Likelihood Ratio Estimation for High- to Zero-frequency N-grams
Masato Kikuchi, Kento Kawakami, Kazuho Watanabe +2
Likelihood ratios (LRs), which are commonly used for probabilistic data processing, are often estimated based on the frequency counts of individual elements obtained from samples.…
Refinement of Direction of Arrival Estimators by Majorization-Minimization Optimization on the Array Manifold
Robin Scheibler, Masahito Togami
We propose a generalized formulation of direction of arrival estimation that includes many existing methods such as steered response power, subspace, coherent and incoherent, as we…
Encoder-Decoder Based Attractors for End-to-End Neural Diarization
Shota Horiguchi, Yusuke Fujita, Shinji Watanabe +2
This paper investigates an end-to-end neural diarization (EEND) method for an unknown number of speakers. In contrast to the conventional cascaded approach to speaker diarization,…
Joint Dereverberation and Separation with Iterative Source Steering
Taishi Nakashima, Robin Scheibler, Masahito Togami +1
We propose a new algorithm for joint dereverberation and blind source separation (DR-BSS). Our work builds upon the IRLMA-T framework that applies a unified filter combining dereve…
Improved parallel WaveGAN vocoder with perceptually weighted spectrogram loss
Eunwoo Song, Ryuichi Yamamoto, Min-Jae Hwang +3
This paper proposes a spectral-domain perceptual weighting technique for Parallel WaveGAN-based text-to-speech (TTS) systems. The recently proposed Parallel WaveGAN vocoder success…
Surrogate Source Model Learning for Determined Source Separation
Robin Scheibler, Masahito Togami
We propose to learn surrogate functions of universal speech priors for determined blind speech separation. Deep speech priors are highly desirable due to their high modelling power…
TTS-by-TTS: TTS-driven Data Augmentation for Fast and High-Quality Speech Synthesis
Min-Jae Hwang, Ryuichi Yamamoto, Eunwoo Song +1
In this paper, we propose a text-to-speech (TTS)-driven data augmentation method for improving the quality of a non-autoregressive (AR) TTS system. Recently proposed non-AR models,…
Parallel waveform synthesis based on generative adversarial networks with voicing-aware conditional discriminators
Ryuichi Yamamoto, Eunwoo Song, Min-Jae Hwang +1
This paper proposes voicing-aware conditional discriminators for Parallel WaveGAN-based waveform synthesis systems. In this framework, we adopt a projection-based conditioning meth…
Independent Vector Analysis via Log-Quadratically Penalized Quadratic Minimization
Robin Scheibler
We propose a new algorithm for blind source separation (BSS) using independent vector analysis (IVA). This is an improvement over the popular auxiliary function based IVA (AuxIVA)…
ID-Conditioned Auto-Encoder for Unsupervised Anomaly Detection
Sławomir Kapka
In this paper, we introduce ID-Conditioned Auto-Encoder for unsupervised anomaly detection. Our method is an adaptation of the Class-Conditioned Auto-Encoder (C2AE) designed for th…
P3GM: Private High-Dimensional Data Release via Privacy Preserving Phased Generative Model
Shun Takagi, Tsubasa Takahashi, Yang Cao +1
How can we release a massive volume of sensitive data while mitigating privacy risks? Privacy-preserving data synthesis enables the data holder to outsource analytical tasks to an…
A study on more realistic room simulation for far-field keyword spotting
Eric Bezzam, Robin Scheibler, Cyril Cadoux +1
We investigate the impact of more realistic room simulation for training far-field keyword spotting systems without fine-tuning on in-domain data. To this end, we study the impact…
Indirect Adversarial Attacks via Poisoning Neighbors for Graph Convolutional Networks
Tsubasa Takahashi
Graph convolutional neural networks, which learn aggregations over neighbor nodes, have achieved great performance in node classification tasks. However, recent studies reported th…
Consistency-aware multi-channel speech enhancement using deep neural networks
Yoshiki Masuyama, Masahito Togami, Tatsuya Komatsu
This paper proposes a deep neural network (DNN)-based multi-channel speech enhancement system in which a DNN is trained to maximize the quality of the enhanced time-domain signal.…
Improving LPCNet-based Text-to-Speech with Linear Prediction-structured Mixture Density Network
Min-Jae Hwang, Eunwoo Song, Ryuichi Yamamoto +2
In this paper, we propose an improved LPCNet vocoder using a linear prediction (LP)-structured mixture density network (MDN). The recently proposed LPCNet vocoder has successfully…
Unsupervised Training for Deep Speech Source Separation with Kullback-Leibler Divergence Based Probabilistic Loss Function
Masahito Togami, Yoshiki Masuyama, Tatsuya Komatsu +1
In this paper, we propose a multi-channel speech source separation with a deep neural network (DNN) which is trained under the condition that no clean signal is available. As an al…
Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram
Ryuichi Yamamoto, Eunwoo Song, Jae-Min Kim
We propose Parallel WaveGAN, a distillation-free, fast, and small-footprint waveform generation method using a generative adversarial network. In the proposed method, a non-autoreg…
ESPnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkit
Tomoki Hayashi, Ryuichi Yamamoto, Katsuki Inoue +6
This paper introduces a new end-to-end text-to-speech (E2E-TTS) toolkit named ESPnet-TTS, which is an extension of the open-source speech processing toolkit ESPnet. The toolkit sup…