Results 21 to 30 of about 598 (156)

Decoding violated sensory expectations from the auditory cortex of anaesthetised mice: Hierarchical recurrent neural network depicts separate ‘danger’ and ‘safety’ units

European Journal of Neuroscience, Volume 56, Issue 3, Page 4154-4175, August 2022., 2022
Multivariate pattern analysis (MVPA) and hierarchical recurrent neural network (RNN) modelling were used to examine the neurophysiology of auditory novelty responses in cortical evoked potentials recorded from anaesthetised mice. Asymmetry between rising and falling sound intensity transitions, in contrast with ascending and descending tone frequency ...
Jamie A. O'Reilly, Thanate Angsuwatanakul, Jordan Wehrman   +2 more
wiley   +1 more source

Intrinsic Disordered Network in Multiferroic YMnO₃ Single Crystals for In-Materio Physical Reservoir Computing Through Tuneable Domain-Wall Structure. [PDF]

Small
Intrinsically disordered cloverleaf domain structures in multiferroic YMnO3 single crystals enable highly nonlinear, thermally stable, and energy‐efficient physical reservoir computing. This system performs waveform generation, time‐series forecasting, and voice recognition at microwatt‐level power, leveraging the anisotropic domain‐wall topology to ...
Xu M, Furuta K, Karacali A, Umezaki Y, Kamarol Zaman AS, Usami Y, Tanaka H, Horibe Y.   +7 more
europepmc   +2 more sources

[Retracted] Research and DSP Implementation of Speech Enhancement Technology Based on Dynamic Mixed Features and Adaptive Mask

Journal of Electrical and Computer Engineering, Volume 2022, Issue 1, 2022., 2022
A deep learning speech enhancement algorithm based on dynamic hybrid feature and adaptive mask and DSP implementation is proposed in this paper, which solves the problem of feature loss and improves the performance of speech enhancement. The dynamic features incorporate the log Mel power spectrum, Mel cepstral coefficients, and Multiresolution Auditory
Jie Yang, Yachun Tang, Wei Liu
wiley   +1 more source

AUC optimization for deep learning-based voice activity detection

EURASIP Journal on Audio, Speech, and Music Processing, 2022
Voice activity detection (VAD) based on deep neural networks (DNN) have demonstrated good performance in adverse acoustic environments. Current DNN-based VAD optimizes a surrogate function, e.g., minimum cross-entropy or minimum squared error, at a given
Xiao-Lei Zhang, Menglong Xu
doaj   +1 more source

In‐Materio Reservoir Computing in a Sulfonated Polyaniline Network

Advanced Materials, Volume 33, Issue 48, December 2, 2021., 2021
A sulfonated polyaniline (SPAN) organic electrochemical network device (OEND) that exhibits ionic conduction in a humid environment is used as an in materio reservoir for reservoir computing (RC). The output behavior indicates wide variations for each electrode, which improves RC performance.
Yuki Usami, Bram van de Ven, Dilu G. Mathew, Tao Chen, Takumi Kotooka, Yuya Kawashima, Yuichiro Tanaka, Yoichi Otsuka, Hiroshi Ohoyama, Hakaru Tamukoh, Hirofumi Tanaka, Wilfred G. van der Wiel, Takuya Matsumoto   +12 more
wiley   +1 more source

Source Localization of EM Waves in the Near‐Field of Spherical Antenna Array in the Presence of Unknown Mutual Coupling

Wireless Communications and Mobile Computing, Volume 2021, Issue 1, 2021., 2021
To obtain an antenna array with isotropic radiation, spherical antenna array (SAA) is the right array configuration. The challenges of locating signals transmitted within the proximity of antenna array have been investigated considerably in the literature.
Oluwole John Famoriji, Thokozani Shongwe, Fawad Zaman   +2 more
wiley   +1 more source

Visually Indicated Sounds [PDF]

, 2016
Objects make distinctive sounds when they are hit or scratched. These sounds reveal aspects of an object's material properties, as well as the actions that produced them.
Adelson, Edward H., Freeman, William T., Isola, Phillip, McDermott, Josh, Owens, Andrew, Torralba, Antonio   +5 more
core   +2 more sources

A New Speech Enhancement Technique Based on Stationary Bionic Wavelet Transform and MMSE Estimate of Spectral Amplitude

Security and Communication Networks, Volume 2021, Issue 1, 2021., 2021
Speech enhancement has gained considerable attention in the employment of speech transmission via the communication channel, speaker identification, speech‐based biometric systems, video conference, hearing aids, mobile phones, voice conversion, microphones, and so on.
Mourad Talbi, Med Salim Bouhlel, Manjit Kaur   +2 more
wiley   +1 more source

Blind speaker identification for audio forensic purposes

Dyna, 2017
This paper presents a blind method for speaker identification for audio forensics purposes. It is based on a decision system with fuzzy rules and works with the correlation between the cochleagrams of the audio proof and of the audios of the suspects ...
Dora Maria Ballesteros-Larrota, Diego Renza-Torres, Steven Andrés Camacho-Vargas   +2 more
doaj   +1 more source

Statistics of natural reverberation enable perceptual separation of sound and space [PDF]

, 2016
In everyday listening, sound reaches our ears directly from a source as well as indirectly via reflections known as reverberation. Reverberation profoundly distorts the sound from a source, yet humans can both identify sound sources and distinguish ...
McDermott, Joshua H., Traer, James A
core   +1 more source