渡邉 紳二

教諭

  • Teacher (Affiliated Senior High School) 教諭, 高等学院
  • 3367 引用
  • 30 h指数
19992019
Pureに変更を加えた場合、すぐここに表示されます。

研究成果 1999 2019

フィルター
Article
2019
2 引用 (Scopus)

Phasebook and friends: Leveraging discrete representations for source separation

Le Roux, J., Wichern, G., Watanabe, S., Sarroff, A. & Hershey, J. R., 2019 5 1, : : IEEE Journal on Selected Topics in Signal Processing. 13, 2, p. 370-382 13 p., 8664086.

研究成果: Article

Source separation
Masks
Speech enhancement
Ceilings
Chemical activation
2018
1 引用 (Scopus)
Evolution Strategies
speech recognition
Speech Recognition
System Development
automation

Model parameter learning using Kullback–Leibler divergence

Lin, C., Marks, T. K., Pajovic, M., Watanabe, S. & Tung, C. K., 2018 2 1, : : Physica A: Statistical Mechanics and its Applications. 491, p. 549-559 11 p.

研究成果: Article

Parameter Learning
Kullback-Leibler Divergence
learning
divergence
Renormalization Group
2017
18 引用 (Scopus)

A Unified Architecture for Multichannel End-to-End Speech Recognition with Neural Beamforming

Ochiai, T., Watanabe, S., Hori, T., Hershey, J. R. & Xiao, X., 2017 10 17, (Accepted/In press) : : IEEE Journal on Selected Topics in Signal Processing.

研究成果: Article

Beamforming
Speech recognition
Speech enhancement
Speech analysis
Hidden Markov models
15 引用 (Scopus)

Duration-Controlled LSTM for Polyphonic Sound Event Detection

Hayashi, T., Watanabe, S., Toda, T., Hori, T., Le Roux, J. & Takeda, K., 2017 11 1, : : IEEE/ACM Transactions on Audio Speech and Language Processing. 25, 11, p. 2059-2070 12 p., 8010445.

研究成果: Article

Event Detection
Long-Term Memory
Memory Term
Short-Term Memory
Acoustic waves
46 引用 (Scopus)

Hybrid CTC/Attention Architecture for End-to-End Speech Recognition

Watanabe, S., Hori, T., Kim, S., Hershey, J. R. & Hayashi, T., 2017 12 1, : : IEEE Journal on Selected Topics in Signal Processing. 11, 8, p. 1240-1253 14 p., 8068205.

研究成果: Article

Speech recognition
Decoding
Linguistics
Hidden Markov models
Acoustics
2 引用 (Scopus)

Multi-microphone speech recognition in everyday environments

Barker, J., Marxer, R., Vincent, E. & Watanabe, S., 2017, (Accepted/In press) : : Computer Speech and Language.

研究成果: Article

Microphones
Speech Recognition
Speech recognition
Speech intelligibility
Microphones
Speech recognition
Decoding
Acoustic waves
2016
63 引用 (Scopus)

An analysis of environment, microphone and data simulation mismatches in robust speech recognition

Vincent, E., Watanabe, S., Nugraha, A. A., Barker, J. & Marxer, R., 2016 4 25, (Accepted/In press) : : Computer Speech and Language.

研究成果: Article

Robust Speech Recognition
Microphones
Speech recognition
Automatic Speech Recognition
Speech enhancement
9 引用 (Scopus)

Context-sensitive and role-dependent spoken language understanding using bidirectional and attention LSTMs

Hori, C., Hori, T., Watanabe, S. & Hershey, J. R., 2016, : : Unknown Journal. 08-12-September-2016, p. 3236-3240 5 p.

研究成果: Article

Hotels
Recurrent neural networks
Dependent
Context sensitive languages
Reservation
3 引用 (Scopus)

Data selection by sequence summarizing neural network in mismatch condition training

Žmolíková, K., Karafiát, M., Veselý, K., Delcroix, M., Watanabe, S., Burget, L. & Cěrnocký, J., 2016, : : Unknown Journal. 08-12-September-2016, p. 2354-2358 5 p.

研究成果: Article

education
Acoustics
Neural Networks
Neural networks
Reverberation
78 引用 (Scopus)

Improved MVDR beamforming using single-channel mask prediction networks

Erdogan, H., Hershey, J., Watanabe, S., Mandel, M. & Le Roux, J., 2016, : : Unknown Journal. 08-12-September-2016, p. 1981-1985 5 p.

研究成果: Article

Minimum Variance
beamforming
Beamforming
Mask
Masks
9 引用 (Scopus)

Multi-microphone speech recognition integrating beamforming, robust feature extraction, and advanced DNN/RNN backend

Hori, T., Chen, Z., Erdogan, H., Hershey, J. R., Le Roux, J., Mitra, V. & Watanabe, S., 2016 4 11, (Accepted/In press) : : Computer Speech and Language.

研究成果: Article

Recurrent neural networks
Recurrent Neural Networks
Beamforming
Microphones
Speech Recognition
77 引用 (Scopus)

Single-channel multi-speaker separation using deep clustering

Isik, Y., Le Roux, J., Chen, Z., Watanabe, S. & Hershey, J. R., 2016, : : Unknown Journal. 08-12-September-2016, p. 545-549 5 p.

研究成果: Article

Clustering
Baseline
education
Enhancement
Speech recognition
25 引用 (Scopus)

The third 'CHiME' speech separation and recognition challenge: Analysis and outcomes

Barker, J., Marxer, R., Vincent, E. & Watanabe, S., 2016 4 25, (Accepted/In press) : : Computer Speech and Language.

研究成果: Article

Speech recognition
Speech Recognition
Evaluation
Baseline
Mobile devices
Speech recognition
Acoustics
Acoustic waves
Speech enhancement
Reverberation
12 引用 (Scopus)

Efficient learning for spoken language understanding tasks with word embedding based pre-training

Luan, Y., Watanabe, S. & Harsham, B., 2015, : : Unknown Journal. 2015-January, p. 1398-1402 5 p.

研究成果: Article

Recurrent neural networks
embedding
learning
Recurrent Neural Networks
education
43 引用 (Scopus)

Speech enhancement and recognition using multi-task learning of long short-term memory recurrent neural networks

Chen, Z., Watanabe, S., Erdogan, H. & Hershey, J. R., 2015, : : Unknown Journal. 2015-January, p. 3274-3278 5 p.

研究成果: Article

Multi-task Learning
Speech Enhancement
Speech enhancement
Automatic Speech Recognition
Memory Term
17 引用 (Scopus)

Uncertainty propagation through deep neural networks

Abdelaziz, A. H., Watanabe, S., Hershey, J. R., Vincent, E. & Kolossa, D., 2015, : : Unknown Journal. 2015-January, p. 3561-3565 5 p.

研究成果: Article

Uncertainty Propagation
Acoustics
Neural Networks
Uncertainty
Acoustic Model
7 引用 (Scopus)
Stochastic Representation
Automatic Speech Recognition
speech recognition
decoding
Speech recognition
2014
4 引用 (Scopus)

Cost-level integration of statistical and rule-based dialog managers

Watanabe, S., Hershey, J. R., Marks, T. K., Fujii, Y. & Koji, Y., 2014, : : Unknown Journal. p. 323-327 5 p.

研究成果: Article

Managers
costs
Costs
Knowledge based systems
Rule-based Systems
63 引用 (Scopus)

Discriminative NMF and its application to single-channel source separation

Weninger, F., Le Roux, J., Hershey, J. R. & Watanabe, S., 2014, : : Unknown Journal. p. 865-869 5 p.

研究成果: Article

Source separation
Source Separation
Matrix Factorization
Factorization
factorization
1 引用 (Scopus)

Sequential maximum mutual information linear discriminant analysis for speech recognition

Tachioka, Y., Watanabe, S., Le Roux, J. & Hershey, J. R., 2014, : : Unknown Journal. p. 2415-2419 5 p.

研究成果: Article

speech recognition
Discriminant analysis
Speech Recognition
Discriminant Analysis
Mutual Information
8 引用 (Scopus)

Structural bayesian linear regression for hidden markov models

Watanabe, S., Nakamura, A. & Juang, B. H., 2014, : : Journal of Signal Processing Systems. 74, 3, p. 341-358 18 p.

研究成果: Article

Hidden Markov models
Linear regression
Markov Model
Tree Structure
Lower bound
2013
10 引用 (Scopus)
Speech Enhancement
Speech enhancement
Uncertainty
Robust Speech Recognition
Acoustic Model
4 引用 (Scopus)

Discriminative training of acoustic models for system combination

Tachioka, Y. & Watanabe, S., 2013, : : Unknown Journal. p. 2355-2359 5 p.

研究成果: Article

Discriminative Training
Acoustic Model
Speech recognition
Labels
education
3 引用 (Scopus)
augmentation
linear transformations
Linear transformations
speech recognition
Speech recognition
2 引用 (Scopus)

Influence relation estimation based on lexical entrainment in conversation

Iwata, T. & Watanabe, S., 2013 2, : : Speech Communication. 55, 2, p. 329-339 11 p.

研究成果: Article

Entrainment
conversation
Experiments
Expectation-maximization Algorithm
Weighted Sums
1 引用 (Scopus)

Prior-shared feature and model space speaker adaptation by consistently employing map estimation

Hahm, S. J., Watanabe, S., Ogawa, A., Fujimoto, M., Hori, T. & Nakamura, A., 2013, : : Speech Communication. 55, 3, p. 415-431 17 p.

研究成果: Article

MAP Estimation
Speaker Adaptation
Maximum a Posteriori
Prior distribution
Linear regression
19 引用 (Scopus)

Speech recognition in living rooms: Integrated speech enhancement and recognition system based on spatial, spectral and temporal modeling of sounds

Delcroix, M., Kinoshita, K., Nakatani, T., Araki, S., Ogawa, A., Hori, T., Watanabe, S., Fujimoto, M., Yoshioka, T., Oba, T., Kubo, Y., Souden, M., Hahm, S. J. & Nakamura, A., 2013 5 3, : : Computer Speech and Language. 27, 3, p. 851-873 23 p., 547.

研究成果: Article

Speech Enhancement
Speech enhancement
Speech Recognition
Speech recognition
Acoustic waves
1 引用 (Scopus)
Sensors
Labels
End users
Modeling
Sensor
2012
Bayesian approach
Modeling
Approximation
Speech recognition
Machine learning
8 引用 (Scopus)
Voice Activity Detection
normalization
Pruning
Normalization
Gaussian Mixture Model
54 引用 (Scopus)

Low-Latency Real-Time Meeting Recognition and Understanding Using Distant Microphones and Omni-Directional Camera

Hori, T., Araki, S., Yoshioka, T., Fujimoto, M., Watanabe, S., Oba, T., Ogawa, A., Kinoshita, K., Nakatani, T., Nakamura, A., Otsuka, K., Mikami, D. & Yamato, J., 2012, : : IEEE Transactions on Audio, Speech and Language Processing. 20, 2, p. 499-513 15 p.

研究成果: Article

Microphones
microphones
Cameras
cameras
Monitoring
20 引用 (Scopus)

Statistical voice conversion based on noisy channel model

Saito, D., Watanabe, S., Nakamura, A. & Minematsu, N., 2012, : : IEEE Transactions on Audio, Speech and Language Processing. 20, 6, p. 1784-1794 11 p., 6156420.

研究成果: Article

linguistics
Linguistics
education
estimates
Experiments
7 引用 (Scopus)
speech recognition
decoding
Speech recognition
Decoding
decoders
2011
4 引用 (Scopus)

A robust estimation method of noise mixture model for noise suppression

Fujimoto, M., Watanabe, S. & Nakatani, T., 2011, : : Unknown Journal. p. 697-700 4 p.

研究成果: Article

Noise Suppression
Robust Estimation
Mixture Model
retarding
Taylor series
2 引用 (Scopus)

Learning influences fromword use in polylogue

Iwata, T. & Watanabe, S., 2011, : : Unknown Journal. p. 3089-3092 4 p.

研究成果: Article

learning
conversation
Expectation-maximization Algorithm
Probabilistic Model
Experiments
1 引用 (Scopus)

Model adaptation for automatic speech recognition based on multiple time scale evolution

Watanabe, S., Nakamura, A. & Juang, B. H., 2011, : : Unknown Journal. p. 1081-1084 4 p.

研究成果: Article

Multiple Time Scales
Automatic Speech Recognition
speech recognition
Speech recognition
Continuous speech recognition
25 引用 (Scopus)

Topic tracking language model for speech recognition

Watanabe, S., Iwata, T., Hori, T., Sako, A. & Ariki, Y., 2011 4, : : Computer Speech and Language. 25, 2, p. 440-461 22 p.

研究成果: Article

Language Model
Speech Recognition
Speech recognition
Acoustics
Vary
2010
7 引用 (Scopus)
Hidden Markov models
Classifiers
Probability density function
Speech recognition
Maximum likelihood
12 引用 (Scopus)
Classifiers
Free energy
Statistical Models
5 引用 (Scopus)
Acoustics
Speech recognition
Linear regression
Kalman filters
Maximum likelihood
2009
13 引用 (Scopus)
Calculi
functionals
margins
education
integral calculus
48 引用 (Scopus)
preprocessing
Reverberation
reverberation
Acoustic noise
speech recognition

Stereo-input speech recognition using sparseness-based time-frequency masking in a reverberant environment

Izumi, Y., Nishiki, K., Watanabe, S., Nishimoto, T., Ono, N. & Sagayama, S., 2009, : : Unknown Journal. p. 1955-1958 4 p.

研究成果: Article

Speech intelligibility
speech recognition
masking
Speech recognition
Masks
2006
15 引用 (Scopus)
Continuous speech recognition
speech recognition
topology
Acoustics
Topology
3 引用 (Scopus)
Speech recognition
Students
2005
1 引用 (Scopus)

Selection of shared-state Hidden Markov model structure using Bayesian criterion

Watanabe, S., Minami, Y., Nakamura, A. & Ueda, N., 2005 1, : : IEICE Transactions on Information and Systems. E88-D, 1, p. 1-9 9 p.

研究成果: Article

Hidden Markov models
Model structures
Speech analysis
Decision trees
Speech recognition