Zobrazeno 1 - 10
of 846
pro vyhledávání: '"Nakamura, Tomohiko"'
Autor:
Choi, Kwanghee, Pasad, Ankita, Nakamura, Tomohiko, Fukayama, Satoru, Livescu, Karen, Watanabe, Shinji
Self-supervised speech models (S3Ms) have become an effective backbone for speech applications. Various analyses suggest that S3Ms encode linguistic properties. In this work, we seek a more fine-grained analysis of the word-level linguistic propertie
Externí odkaz:
http://arxiv.org/abs/2406.08619
This paper presents a neural method for distant speech recognition (DSR) that jointly separates and diarizes speech mixtures without supervision by isolated signals. A standard separation method for multi-talker DSR is a statistical multichannel meth
Externí odkaz:
http://arxiv.org/abs/2406.08396
Real-time speech extraction is an important challenge with various applications such as speech recognition in a human-like avatar/robot. In this paper, we propose the real-time extension of a speech extraction method based on independent low-rank mat
Externí odkaz:
http://arxiv.org/abs/2403.12477
Autor:
Nakamura, Tomohiko, Yatabe, Kohei
This paper proposes a universal sound separation (USS) method capable of handling untrained sampling frequencies (SFs). The USS aims at separating arbitrary sources of different types and can be the key technique to realize a source separator that ca
Externí odkaz:
http://arxiv.org/abs/2309.12581
Publikováno v:
European Signal Processing Conference, Sep. 2023, pp. 326--330
In this paper, we propose algorithms for handling non-integer strides in sampling-frequency-independent (SFI) convolutional and transposed convolutional layers. The SFI layers have been developed for handling various sampling frequencies (SFs) by a s
Externí odkaz:
http://arxiv.org/abs/2306.10718
Autor:
Park, Joonyong, Takamichi, Shinnosuke, Nakamura, Tomohiko, Seki, Kentaro, Xin, Detai, Saruwatari, Hiroshi
We examine the speech modeling potential of generative spoken language modeling (GSLM), which involves using learned symbols derived from data rather than phonemes for speech analysis and synthesis. Since GSLM facilitates textless spoken language pro
Externí odkaz:
http://arxiv.org/abs/2306.00697
Autor:
Nakamura, Tomohiko, Takamichi, Shinnosuke, Tanji, Naoko, Fukayama, Satoru, Saruwatari, Hiroshi
Publikováno v:
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Jun. 2023, 5 pages
We construct a corpus of Japanese a cappella vocal ensembles (jaCappella corpus) for vocal ensemble separation and synthesis. It consists of 35 copyright-cleared vocal ensemble songs and their audio recordings of individual voice parts. These songs w
Externí odkaz:
http://arxiv.org/abs/2211.16028
Hyperbolic Timbre Embedding for Musical Instrument Sound Synthesis Based on Variational Autoencoders
Autor:
Nakashima, Futa, Nakamura, Tomohiko, Takamune, Norihiro, Fukayama, Satoru, Saruwatari, Hiroshi
Publikováno v:
2022 Asia Pacific Signal and Information Processing Association Annual Summit and Conference
In this paper, we propose a musical instrument sound synthesis (MISS) method based on a variational autoencoder (VAE) that has a hierarchy-inducing latent space for timbre. VAE-based MISS methods embed an input signal into a low-dimensional latent re
Externí odkaz:
http://arxiv.org/abs/2209.13211
We propose a method of head-related transfer function (HRTF) interpolation from sparsely measured HRTFs using an autoencoder with source position conditioning. The proposed method is drawn from an analogy between an HRTF interpolation method based on
Externí odkaz:
http://arxiv.org/abs/2207.10967
A sound field estimation method based on a physics-informed convolutional neural network (PICNN) using spline interpolation is proposed. Most of the sound field estimation methods are based on wavefunction expansion, making the estimated function sat
Externí odkaz:
http://arxiv.org/abs/2207.10937