Results 51 to 60 of about 132,794 (332)

Silent speech command word recognition using stepped frequency continuous wave radar

Scientific Reports, 2022
Recovering speech in the absence of the acoustic speech signal itself, i.e., silent speech, holds great potential for restoring or enhancing oral communication in those who lost it.
Christoph Wagner, Petr Schaffer, Pouriya Amini Digehsara, Michael Bärhold, Dirk Plettemeier, Peter Birkholz   +5 more
doaj   +1 more source

Corpus of deaf speech for acoustic and speech production research [PDF]

The Journal of the Acoustical Society of America, 2017
A corpus of recordings of deaf speech is introduced. Adults who were pre- or post-lingually deafened as well as those with normal hearing read standardized speech passages totaling 11 h of .wav recordings. Preliminary acoustic analyses are included to provide a glimpse of the kinds of analyses that can be conducted with this corpus of recordings.
Lisa Lucks, Mendel, Sungmin, Lee, Monique, Pousson, Chhayakanta, Patro, Skylar, McSorley, Bonny, Banerjee, Shamima, Najnin, Masoumeh Heidari, Kapourchali   +7 more
openaire   +2 more sources

Moth‐Wing‐Inspired Multifunctional Metamaterials

Advanced Materials, EarlyView.
This study develops a moth‐wing‐inspired heterogeneous metamaterial that achieves synergistic broadband sound absorption, mechanical energy dissipation, and thermal insulation within a lightweight architected framework. Combining bioinspired gradient design, genetic‐algorithm optimization, and additive manufacturing, the bionic heterogeneous acoustic ...
Haoran Pei, Hang Yang, Ning Zhang, Tian Li, Xinxin Wang, Miao Zhao, Shuwei Ding, Xin Wang, Qinniu Lv, Zijie Xu, Yinghong Chen, Xinwei Li, Wei Zhai   +12 more
wiley   +1 more source

Two-Stage Domain Adaptation for LLM-Based ASR by Decoupling Linguistic and Acoustic Factors

Applied Sciences
Large language models (LLMs) have been increasingly applied in Automatic Speech Recognition (ASR), achieving significant advancements. However, the performance of LLM-based ASR (LLM-ASR) models remains unsatisfactory when applied across domains due to ...
Lin Zheng, Xuyang Wang, Qingwei Zhao, Ta Li   +3 more
doaj   +1 more source

On the acoustics of overlapping laughter in conversational speech [PDF]

, 2012
The social nature of laughter invites people to laugh together. This joint vocal action often results in overlapping laughter. In this paper, we show that the acoustics of overlapping laughs are different from non-overlapping laughs.
Trouvain, Jürgen, Truong, Khiet P.
core   +2 more sources

Observation of Dislocation Bound States and Skin Effects in Non‐Hermitian Chern Insulators

Advanced Materials, EarlyView.
Experimental observation of the dislocation‐induced bound states and skin effects is demonstrated in a line‐gap non‐Hermitian acoustic lattice. By utilizing active meta‐atoms to measure the full complex spectrum and biorthogonal eigenstates, the study reveals the exceptional‐point‐driven melting of defect modes.
Jia‐Xin Zhong, Bitan Roy, Yun Jing
wiley   +1 more source

LWMD: A Comprehensive Compression Platform for End-to-End Automatic Speech Recognition Models

Applied Sciences, 2023
Recently end-to-end (E2E) automatic speech recognition (ASR) models have achieved promising performance. However, existing models tend to adopt increasing model sizes and suffer from expensive resource consumption for real-world applications. To compress
Yukun Liu, Ta Li, Pengyuan Zhang, Yonghong Yan   +3 more
doaj   +1 more source

Finite-State Channel Models for Signal Transduction in Neural Systems

, 2016
Information theory provides powerful tools for understanding communication systems. This analysis can be applied to intercellular signal transduction, which is a means of chemical communication among cells and microbes.
Eckford, Andrew W., Loparo, Kenneth A., Thomas, Peter J.   +2 more
core   +1 more source

Ferroelectrics Hybrids: Harnessing Multifunctionality of 2D Semiconductors in the Post‐Moore Era

Advanced Materials, EarlyView.
In this Review, the state of art of ferroelectric hybrid systems—combining ferroelectrics, 2D semiconductors, and molecular switches is presented—as next‐generation platforms for high‐density, multifunctional electronics. By discussing 2D FeFET applications, nanoscale material downscaling, M3D integration, and emerging ferroelectrics, it highlights ...
Haixin Qiu, Xiaoshi Qian, Dahong Qian, Paolo Samorì   +3 more
wiley   +1 more source

Adding Prior Knowledge in Hierarchical Attention Neural Network for Cross Domain Sentiment Classification

IEEE Access, 2019
Domain adaptation tasks have raised much attention in recent years, especially, the task of cross-domain sentiment classification (CDSC). Due to the domain discrepancy, a sentiment classifier trained in a source domain often performs less well, when ...
Tu Manshu, Wang Bing
doaj   +1 more source