Hiroshi Saruwatari mostly deals with Speech recognition, Blind signal separation, Algorithm, Artificial intelligence and Speech processing. His Speech recognition research incorporates elements of Speech enhancement, Microphone array and Noise reduction. His research integrates issues of Independent component analysis, Frequency domain and Reverberation in his study of Blind signal separation.
His Algorithm research is multidisciplinary, incorporating elements of Low frequency and Beamforming. His Artificial intelligence study combines topics in areas such as Natural language processing, Loudspeaker and Pattern recognition. His work focuses on many connections between Speech processing and other disciplines, such as Finite impulse response, that overlap with his field of interest in Learning rule, Adaptive filter and Time domain.
Hiroshi Saruwatari mainly investigates Speech recognition, Blind signal separation, Artificial intelligence, Algorithm and Independent component analysis. He specializes in Speech recognition, namely Speech processing. His Blind signal separation research focuses on subjects like Frequency domain, which are linked to Reverberation.
His work on Speech synthesis as part of general Artificial intelligence study is frequently linked to Non-negative matrix factorization, bridging the gap between disciplines. His study in the field of Covariance function is also linked to topics like Matrix analysis, Convergence and Low-rank approximation. His study in Pattern recognition is interdisciplinary in nature, drawing from both Separation and Spectrogram.
His main research concerns Algorithm, Speech recognition, Artificial neural network, Blind signal separation and Speech synthesis. His study on Source separation is often connected to Non-negative matrix factorization, Matrix analysis and Basis as part of broader study in Algorithm. His Language model study in the realm of Speech recognition connects with subjects such as Domain adaptation.
In his research, Prosody is intimately related to Context, which falls under the overarching field of Artificial neural network. His Blind signal separation study combines topics from a wide range of disciplines, such as Multivariate normal distribution, Multivariate statistics and Generative model. He interconnects Mixture model, Spectral envelope and Automatic summarization in the investigation of issues within Speech synthesis.
Speech recognition, Algorithm, Blind signal separation, Speech synthesis and Artificial neural network are his primary areas of study. His work carried out in the field of Speech recognition brings together such families of science as Backpropagation, Singing, Discriminator, Variety and Similarity. His Algorithm study incorporates themes from Weighting, Active noise control, Loudspeaker, Noise reduction and Kernel.
Blind signal separation and Covariance function are frequently intertwined in his study. His research investigates the connection with Speech synthesis and areas like Rule-based machine translation which intersect with concerns in Prosody. The concepts of his Artificial intelligence study are interwoven with issues in Multivariate statistics and Pattern recognition.
This overview was generated by a machine learning system which analysed the scientist’s body of work. If you have any feedback, you can contact us here.
The fundamental limitation of frequency domain blind source separation for convolutive mixtures of speech
S. Araki;R. Mukai;S. Makino;T. Nishikawa.
IEEE Transactions on Speech and Audio Processing (2003)
Evaluation of blind signal separation method using directivity pattern under reverberant conditions
S. Kurita;H. Saruwatari;S. Kajita;K. Takeda.
international conference on acoustics, speech, and signal processing (2000)
Blind source separation combining independent component analysis and beamforming
Hiroshi Saruwatari;Satoshi Kurita;Kazuya Takeda;Fumitada Itakura.
EURASIP Journal on Advances in Signal Processing (2003)
Determined blind source separation unifying independent vector analysis and nonnegative matrix factorization
Daichi Kitamura;Nobutaka Ono;Hiroshi Sawada;Hirokazu Kameoka.
IEEE Transactions on Audio, Speech, and Language Processing (2016)
Blind source separation based on a fast-convergence algorithm combining ICA and beamforming
H. Saruwatari;T. Kawamura;T. Nishikawa;A. Lee.
IEEE Transactions on Audio, Speech, and Language Processing (2006)
Voice conversion algorithm based on Gaussian mixture model with dynamic frequency warping of STRAIGHT spectrum
T. Toda;H. Saruwatari;K. Shikano.
international conference on acoustics, speech, and signal processing (2001)
Statistical Parametric Speech Synthesis Incorporating Generative Adversarial Networks
Yuki Saito;Shinnosuke Takamichi;Hiroshi Saruwatari.
IEEE Transactions on Audio, Speech, and Language Processing (2018)
Speaking-aid systems using GMM-based voice conversion for electrolaryngeal speech
Keigo Nakamura;Tomoki Toda;Hiroshi Saruwatari;Kiyohiro Shikano.
Speech Communication (2012)
Blind Spatial Subtraction Array for Speech Enhancement in Noisy Environment
Y. Takahashi;T. Takatani;K. Osako;H. Saruwatari.
IEEE Transactions on Audio, Speech, and Language Processing (2009)
Maximum Likelihood Voice Conversion Based on GMM with STRAIGHT Mixed Excitation
Yamato Ohtani;Tomoki Toda;Hiroshi Saruwatari;Kiyohiro Shikano.
conference of the international speech communication association (2006)
If you think any of the details on this page are incorrect, let us know.
We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below: