Results 51 to 60 of about 23,835 (260)

Prosodic-Enhanced Siamese Convolutional Neural Networks for Cross-Device Text-Independent Speaker Verification

open access: yes, 2018
In this paper a novel cross-device text-independent speaker verification architecture is proposed. Majority of the state-of-the-art deep architectures that are used for speaker verification tasks consider Mel-frequency cepstral coefficients. In contrast,
Dabouei, Ali   +5 more
core   +1 more source

Recognition of elementary arm movements using orientation of a tri-axial accelerometer located near the wrist [PDF]

open access: yes, 2014
In this paper we present a method for recognising three fundamental movements of the human arm (reach and retrieve, lift cup to mouth, rotation of the arm) by determining the orientation of a tri-axial accelerometer located near the wrist.
Achner, Josy   +8 more
core   +1 more source

Voice and Speech in Atypical Parkinsonian Disorders

open access: yesMovement Disorders Clinical Practice, EarlyView.
Background Motor speech disorders are early, common, and functionally limiting features of atypical parkinsonian disorders (APDs) such as progressive supranuclear palsy (PSP), corticobasal syndrome (CBS), and multiple system atrophy (MSA). These impairments are underrecognized and undertreated in neurology clinics.
Federico Rodriguez‐Porcel   +48 more
wiley   +1 more source

Impact of laryngopharyngeal reflux on subjective and objective voice assessments: A prospective study

open access: yesJournal of Otolaryngology - Head and Neck Surgery, 2016
Background Laryngopharyngeal reflux is a prevalent, not well-understood disease affecting a high proportion of patients who seek laryngology consultation.
Jérôme R. Lechien   +7 more
doaj   +1 more source

Compare acoustic analysis in children with VPI and normal

open access: yesمجله پژوهش در علوم توانبخشی, 2012
Introduction: It has been hypothesized that speakers with velopharyngeal disorders exert stronger forces on their laryngeal structures in order to minimize hypernasality and to reach appropriate voice intensity.
Fariba Mojiri   +4 more
doaj   +1 more source

Jitter and Shimmer measurements for speaker diarization [PDF]

open access: yes, 2014
Jitter and shimmer voice quality features have been successfully used to characterize speaker voice traits and detect voice pathologies. Jitter and shimmer measure variations in the fundamental frequency and amplitude of speaker's voice, respectively.
Hernando Pericás, Francisco Javier   +2 more
core  

Speaker-independent emotion recognition exploiting a psychologically-inspired binary cascade classification schema

open access: yes, 2012
In this paper, a psychologically-inspired binary cascade classification schema is proposed for speech emotion recognition. Performance is enhanced because commonly confused pairs of emotions are distinguishable from one another.
A. Austermann   +65 more
core   +1 more source

Automatic depression scale prediction using facial expression dynamics and regression [PDF]

open access: yes, 2014
Depression is a state of low mood and aversion to activity that can affect a person's thoughts, behaviour, feelings and sense of well-being. In such a low mood, both the facial expression and voice appear different from the ones in normal states. In this
Asim Jan   +5 more
core   +1 more source

Revealing Intrinsic Functionalization, Structure, and Photo‐Thermal Oxidation in Hexagonal Antimonene

open access: yesSmall, EarlyView.
Cross‐sectional electron microscopy reveals that antimonene hexagons exhibited inner defects and protective organic functionalization against oxidation. Temperature and power‐dependent Raman spectroscopy on varying thicknesses of FLA hexagons show that thinner flakes (<20 nm) exhibited a blueshift and intensity decrease, contrasting with the redshift ...
Marta Alcaraz   +6 more
wiley   +1 more source

Forensic Comparison of Acoustic Voice Samples Recorded in Different Mobile Phone Devices: A Preliminary Study

open access: yesJournal of Forensic Science and Medicine
Background: The nature of voice as forensic evidence holds immense value. The voice examination is highly influenced by various factors such as recording devices, environmental factors, and individual health conditions beyond the norm.
Bhavya Sharma   +4 more
doaj   +1 more source

Home - About - Disclaimer - Privacy