Results 61 to 70 of about 460,856 (296)
On Feature Importance and Interpretability of Speaker Representations [PDF]
, 2023 Unsupervised speech disentanglement aims at separating fast varying from slowly varying components of a speech signal. In this contribution, we take a closer look at the embedding vector representing the slowly varying signal components, commonly named ...
Haeb-Umbach, Reinhold +5 more
core
Advanced Engineering Materials, EarlyView.More than 10 000 metal‐coated silicon MEMS cantilevers are fabricated and characterized to build a large‐scale experimental dataset spanning multiple vibrational modes. Machine learning algorithms are benchmarked to predict resonance frequency and quality factor, with ensemble based models achieving accuracy approaching experimental uncertainty.
Sina Zare Pakzad +8 more
wiley +1 more source
Jordanian Journal of Computers and Information TechnologyBeyond the immediate content of speech, the voice can provide rich information about a speaker's demographics, including age and gender. Estimating a speaker's age and gender offers a wide range of applications, spanning from voice forensic ...
Alia Karim Abdulhassan +1 more
doaj +1 more source
Human-in-the-loop Speaker Adaptation for DNN-based Multi-speaker TTS
, 2022 This paper proposes a human-in-the-loop speaker-adaptation method for multi-speaker text-to-speech. With a conventional speaker-adaptation method, a target speaker's embedding vector is extracted from his/her reference speech using a speaker encoder ...
Saruwatari, Hiroshi +2 more
core
An Edible Chitosan‐Based Acoustic Sensor for Sound‐Responsive Actuation in Edible Robots
Advanced Functional Materials, EarlyView.This study introduces an edible acoustic sensor for robotic food and edible robotics. Built from a chitosan piezoelectric film between gold electrodes, the sensor enables acoustic communication through ON/OFF keying. Integrated into an edible robot with pneumatically actuated arms and neck, it responds to high‐frequency tones.
Valerio Francesco Annese +8 more
wiley +1 more source
InformationChinese short-form dramas (duanju) drive a growing demand for automated Japanese dubbing that preserves each character’s voice. The decisive component is zero-shot cross-lingual voice cloning: synthesising Japanese speech from a short Chinese reference ...
Jing An, Qiming Bao, Jinhua Su
doaj +1 more source
2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)Speaker clustering is the task of identifying the unique speakers in a set of audio recordings (each belonging to exactly one speaker) without knowing who and how many speakers are present in the entire data, which is essential for speaker diarization processes.
Chaohao Lin +4 more
openaire +3 more sources
Fiber‐Based Wearable Electronics as Adaptive Biointerfaces for Healthcare Applications
Advanced Functional Materials, EarlyView.Fiber‐based wearable electronics have been extensively studied as adaptive healthcare biointerfaces. In this review, we classify and introduce fiber‐based systems according to biointerface design, conductive materials, transduction mechanisms, and healthcare applications, and provide a perspective on their translation toward reliable, continuous ...
Sangwoo Hong +5 more
wiley +1 more source
Self Attention Networks in Speaker Recognition
Applied Sciences, 2023 Recently, there has been a significant surge of interest in Self-Attention Networks (SANs) based on the Transformer architecture. This can be attributed to their notable ability for parallelization and their impressive performance across various Natural ...
Pooyan Safari +2 more
doaj +1 more source
Advanced Healthcare Materials, EarlyView.This study shows crosstalk among tumor cells, fibroblasts, and macrophages alters the physical forces inside 3D tumor spheroids. Incorporating deformable microparticles in 3D tumor spheroids, the researchers mapped mechanical stresses spatially and with respect to tumor growth (temporally).
Kunal P. Pednekar +2 more
wiley +1 more source