Zobrazeno 1 - 10
of 184
pro vyhledávání: '"Higuchi Takuya"'
Autor:
Aldeneh, Zakaria, Higuchi, Takuya, Jung, Jee-weon, Chen, Li-Wei, Shum, Stephen, Abdelaziz, Ahmed Hussen, Watanabe, Shinji, Likhomanenko, Tatiana, Theobald, Barry-John
Iterative self-training, or iterative pseudo-labeling (IPL)--using an improved model from the current iteration to provide pseudo-labels for the next iteration--has proven to be a powerful approach to enhance the quality of speaker representations. R
Externí odkaz:
http://arxiv.org/abs/2409.10791
Autor:
Chen, Li-Wei, Higuchi, Takuya, Bai, He, Abdelaziz, Ahmed Hussen, Rudnicky, Alexander, Watanabe, Shinji, Likhomanenko, Tatiana, Theobald, Barry-John, Aldeneh, Zakaria
Speech foundation models, such as HuBERT and its variants, are pre-trained on large amounts of unlabeled speech for various downstream tasks. These models use a masked prediction objective, where the model learns to predict information about masked i
Externí odkaz:
http://arxiv.org/abs/2409.10788
Autor:
Aldeneh, Zakaria, Thilak, Vimal, Higuchi, Takuya, Theobald, Barry-John, Likhomanenko, Tatiana
This study explores using embedding rank as an unsupervised evaluation metric for general-purpose speech encoders trained via self-supervised learning (SSL). Traditionally, assessing the performance of these encoders is resource-intensive and require
Externí odkaz:
http://arxiv.org/abs/2409.10787
Non-negative Matrix Factorization (NMF) is a powerful technique for analyzing regularly-sampled data, i.e., data that can be stored in a matrix. For audio, this has led to numerous applications using time-frequency (TF) representations like the Short
Externí odkaz:
http://arxiv.org/abs/2404.04439
Autor:
Aldeneh, Zakaria, Higuchi, Takuya, Jung, Jee-weon, Seto, Skyler, Likhomanenko, Tatiana, Shum, Stephen, Abdelaziz, Ahmed Hussen, Watanabe, Shinji, Theobald, Barry-John
Self-supervised features are typically used in place of filter-bank features in speaker verification models. However, these models were originally designed to ingest filter-bank features as inputs, and thus, training them on top of self-supervised fe
Externí odkaz:
http://arxiv.org/abs/2402.00340
Autor:
Jung, Jee-weon, Zhang, Wangyou, Shi, Jiatong, Aldeneh, Zakaria, Higuchi, Takuya, Theobald, Barry-John, Abdelaziz, Ahmed Hussen, Watanabe, Shinji
This paper introduces ESPnet-SPK, a toolkit designed with several objectives for training speaker embedding extractors. First, we provide an open-source platform for researchers in the speaker recognition community to effortlessly build models. We pr
Externí odkaz:
http://arxiv.org/abs/2401.17230
Noise robustness is a key aspect of successful speech applications. Speech enhancement (SE) has been investigated to improve automatic speech recognition accuracy; however, its effectiveness for keyword spotting (KWS) is still under-investigated. In
Externí odkaz:
http://arxiv.org/abs/2309.16060
Voice triggering (VT) enables users to activate their devices by just speaking a trigger phrase. A front-end system is typically used to perform speech enhancement and/or separation, and produces multiple enhanced and/or separated signals. Since conv
Externí odkaz:
http://arxiv.org/abs/2309.16036
Autor:
Kozák Martin, Higuchi Takuya, McNeur Joshua, Shiloh Roy, Heide Christian, Paschen Timo, Yousefi Peyman, Sturm Constanze, Li Ang, Illmer Johannes, Meier Stefan, Schönenberger Norbert, Dienstbier Philip, Tafel Alexander, Weber Philipp, Zimmermann Robert, Seidling Michael, Mittelbach Anna, Heimerl Jonas, Eckstein Timo, Hundhausen Martin, Ristein Jürgen, Hommelhoff Peter
Publikováno v:
EPJ Web of Conferences, Vol 205, p 08009 (2019)
New ways of controlling quasi-free and free electrons by means of phase-controlled ultrashort laser pulses are demonstrated: from strong-field physics in the conducting 2-d material graphene and at the surface of nanostructures, to laser acceleration
Externí odkaz:
https://doaj.org/article/6f1e6eb3c694457ea2e3c48a6a05bf6c
Publikováno v:
EPJ Web of Conferences, Vol 205, p 05002 (2019)
We demonstrate that currents induced in graphene by ultrashort laser pulses are sensitive to the exact shape of the electric-field waveform. By increasing the field strength, we found a transition of the light–matter interaction from the weak-field
Externí odkaz:
https://doaj.org/article/9197925bfd3043dc91582072342910ec