Zobrazeno 1 - 10
of 44
pro vyhledávání: '"Togami, Masahito"'
While neural network approaches have made significant strides in resolving classical signal processing problems, it is often the case that hybrid approaches that draw insight from both signal processing and neural networks produce more complete solut
Externí odkaz:
http://arxiv.org/abs/2402.06683
Autor:
Togami, Masahito, Valin, Jean-Marc, Helwani, Karim, Giri, Ritwik, Isik, Umut, Goodwin, Michael M.
We introduce a real-time, multichannel speech enhancement algorithm which maintains the spatial cues of stereo recordings including two speech sources. Recognizing that each source has unique spatial information, our method utilizes a dual-path struc
Externí odkaz:
http://arxiv.org/abs/2402.00337
Autor:
Scheibler, Robin, Togami, Masahito
Publikováno v:
Proc. IEEE ICASSP, pp. 436-440, June, 2021
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 well as speech sparsity-based methods. Unlike most conventional methods
Externí odkaz:
http://arxiv.org/abs/2106.01011
This paper proposes a novel label-synchronous speech-to-text alignment technique for automatic speech recognition (ASR). The speech-to-text alignment is a problem of splitting long audio recordings with un-aligned transcripts into utterance-wise pair
Externí odkaz:
http://arxiv.org/abs/2104.10328
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 dereverberation and separation. One drawback of this framework is that it re
Externí odkaz:
http://arxiv.org/abs/2102.06322
Autor:
Scheibler, Robin, Togami, Masahito
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, but are not compatible with state-of-the-art independent vector anal
Externí odkaz:
http://arxiv.org/abs/2011.05540
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. DNN-based multi-channel speech enhancement is often conducted in the t
Externí odkaz:
http://arxiv.org/abs/2002.05831
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 alternative to a clean signal, the proposed method adopts an estimated s
Externí odkaz:
http://arxiv.org/abs/1911.04228
Autor:
Togami, Masahito
In this paper, a multi-channel time-varying covariance matrix model for late reverberation reduction is proposed. Reflecting that variance of the late reverberation is time-varying and it depends on past speech source variance, the proposed model is
Externí odkaz:
http://arxiv.org/abs/1910.08710
In this paper, we propose two mask-based beamforming methods using a deep neural network (DNN) trained by multichannel loss functions. Beamforming technique using time-frequency (TF)-masks estimated by a DNN have been applied to many applications whe
Externí odkaz:
http://arxiv.org/abs/1907.04984