Skip to Main Content Area
CPS-VO
Contact Support
Browse
Calendar
Announcements
Repositories
Groups
Search
Search for Content
Search for a Group
Search for People
Search for a Project
Tagcloud
› Go to login screen
Not a member?
Click here to register!
Forgot username or password?
Cyber-Physical Systems Virtual Organization
Read-only archive of site from September 29, 2023.
CPS-VO
Speech
biblio
A Hierarchy-to-Sequence Attentional Neural Machine Translation Model
Submitted by grigby1 on Mon, 10/05/2020 - 1:01pm
semantic compositionality modeling
neural nets
optimal model parameters
parameter learning
pubcrawl
recurrent neural nets
Recurrent neural networks
segmented clause sequence
segmented clauses
neural machine translation
Semantics
sequence-to-sequence attentional neural machine translation
short clauses
Speech
speech processing
text analysis
Training
translation prediction
hierarchical neural network structure
Chinese-English translation
clause level
Compositionality
Context modeling
conventional NMT model
Decoding
English-German translation
grammars
attention models
Hierarchy-to-sequence
hierarchy-to-sequence attentional neural machine translation model
hierarchy-to-sequence attentional NMT model
language translation
learning (artificial intelligence)
long parallel sentences
natural language processing
biblio
Authorship Attribution for Social Media Forensics
Submitted by grigby1 on Mon, 03/19/2018 - 12:38pm
social networking (online)
multimodal data processing
prepaid SIM cards
pubcrawl
public Wi-Fi hotspots
smart phones
Smartphones
social media
social media forensics
Metrics
Speech
stylometry
supervised learning-based
user anonymity
user identification
Writing
writing style
authorship attribution
Media
machine learning algorithms
machine learning
learning (artificial intelligence)
internet
Human behavior
habit peculiarities
Forensics
feature extraction
distributed networks
Digital Forensics
context exploitation
Context
computational linguistics
authorship attribution algorithm
biblio
Audio-CAPTCHA with distinction between random phoneme sequences and words spoken by multi-speaker
Submitted by grigby1 on Wed, 12/20/2017 - 12:03pm
pubcrawl
Human behavior
Human Factors
composability
CAPTCHA
captchas
distortion
Proposals
Semantics
Speech
Speech recognition
usability
human beings
biblio
"An improved speech enhancement approach based on combination of compressed sensing and Kalman filter"
Submitted by grigby1 on Tue, 02/21/2017 - 11:33am
noisy speech signal reconstruction
Wiener filters
Wiener filter
speech enhancement techniques
speech enhancement
Speech
Spectral Subtraction
signal subspace
signal reconstruction
pubcrawl170104
objective measures
compressed sensing
Noise measurement
MMSE
Mathematical model
least mean squares methods
Kalman filters
Kalman filter
improved speech enhancement approach
CoSaMP algorithm
compressive sampling matching pursuit
biblio
"Real time secure end to end communication over GSM network"
Submitted by grigby1 on Tue, 02/14/2017 - 11:18am
GSM speech channel
transcoding
speech trans-coding process
Speech
real time secure end to end communication
pubcrawl170102
Modem
mobile phones
Mobile handsets
Mobile communication
cellular radio
GSM network
GSM
encryption
digital techniques
decryption
decoding algorithm
Cryptography
Codecs
biblio
Accurate adaptive filtering in square-root Hann windowed short-time fourier transform domain
Submitted by BrandonB on Wed, 05/06/2015 - 8:38am
noise reduction
square-root Hann windowed STFT domain
square-root Hann window
speech processing
Speech
short-time Fourier transform
residual echo
Prototypes
prototype filter
nonlinear post filters
nonlinear filters
accurate adaptive filtering
linear convolution
frequency-domain analysis
Fourier transforms
echo suppression
Discrete Fourier transforms
convolution
audio signal processing
adaptive filters
Acoustics
acoustic echo cancellation
biblio
An adaptive threshold de-noising method based on EEMD
Submitted by BrandonB on Tue, 05/05/2015 - 9:27am
mode mixing problem
White noise
wavelet-based de-noising method
wavelet transforms
wavelet threshold
wavelet base selection
wavelet analysis
Threshold De-noising
threshold de-noised signal dominant layer
Speech
signal-to-noise boundary layer
Signal to noise ratio
signal reconstruction
signal denoising
noise reduction
noise dominant layer filtering
adaptive
filtering theory
ensemble empirical mode decomposition
Empirical mode decomposition
EEMD
decomposition level selection
de-noising signal reconstruction
de-noised layer component
cross-correlation method
correlation theory
Correlation
autocorrelation method
adaptive threshold de-noising method
adaptive determination correctness verification
adaptive determination correctness analysis
biblio
On the modeling of natural vocal emotion expressions through binary key
Submitted by BrandonB on Mon, 05/04/2015 - 11:03am
natural vocal emotion expression modelling
Vectors
VAM corpus
Training
three-continuous emotional dimensions
support vector regression model
Support vector machines
standard acoustic feature mapping
spontaneous dialogues
Speech recognition
speech features
Speech
spectral parameters
speaker emotion characteristics
regression analysis
acoustic descriptors
mean absolute error
German TV talk-show
feature extraction
emotion recognition
Emotion modeling
dimensional emotions
correlation coefficient
binary value representation
binary key modeling
binary fingerprint
binary acoustic modeling
Acoustics
Acoustic signal processing
biblio
An audio fingerprinting system for live version identification using image processing techniques
Submitted by BrandonB on Mon, 05/04/2015 - 10:48am
image processing techniques
Transforms
Time-frequency Analysis
template matching
speech processing
Speech
Spectrogram
smartphone
Robustness
music festival
log-frequency spectrogram
live version identification
image segmentation
adaptive thresholding
Hough transforms
Hough Transform
Hamming similarity
fingerprint identification
Degradation
cover identification
Constant Q Transform
compact fingerprints
audio signal processing
audio fingerprinting system
Audio fingerprinting
adaptive thresholding method
biblio
Development of a keyboardless social networking website for visually impaired: SocialWeb
Submitted by BrandonB on Mon, 05/04/2015 - 10:33am
message authentication
Web Speech API
visually impaired people
user friendliness
STT conversion
speech to text conversion technologies
Speech recognition
Speech
SocialWeb
social networking (online)
Social network services
screen readers
screen reader
Acoustic Fingerprinting
Media
malicious attackers
keyboardless social networking Website
human computer interaction
handicapped aids
Fingerprint recognition
Computers
computer proficiency
Communities
Audio fingerprinting
Assitive technologies
assistive technologies
1
2
next ›
last »
