Crevasse detection in ice sheets using ground penetrating radar and machine learning

RM Williams, LE Ray, JH Lever… - IEEE Journal of …, 2014 - ieeexplore.ieee.org
This paper presents methods to automatically classify ground penetrating radar (GPR)
images of crevasses on ice sheets. We use a combination of support vector machines …

MMSE-based missing-feature reconstruction with temporal modeling for robust speech recognition

JA González, AM Peinado, N Ma… - IEEE transactions on …, 2012 - ieeexplore.ieee.org
This paper addresses the problem of feature compensation in the log-spectral domain by
using the missing-data (MD) approach to noise robust speech recognition, that is, the log …

Packet loss concealment method based on hidden Markov model and decision tree for AMR-WB codec

T Gueham, F Merazka - Multimedia Tools and Applications, 2024 - Springer
Packet loss concealment (PLC) techniques are utilized to improve the quality of Voice over
IP (VoIP) communications by reconstructing missing speech packets. Hidden Markov Model …

[PDF][PDF] Efficient HMM-based estimation of missing features, with applications to packet loss concealment.

BJ Borgström, PH Borgström, A Alwan - INTERSPEECH, 2010 - isca-archive.org
In this paper, we present efficient HMM-based techniques for estimating missing features. By
assuming speech features to be observations of hidden Markov processes, we derive a …

A wavelet-based thresholding approach to reconstructing unreliable spectrogram components

S Badiezadegan, RC Rose - Speech Communication, 2015 - Elsevier
Data imputation approaches for robust automatic speech recognition reconstruct noise
corrupted spectral information by exploiting prior knowledge of the relationship between …

A GMM/HMM model for reconstruction of missing speech spectral components for continuous speech recognition

MM Goodarzi, F Almasganj - International Journal of Speech Technology, 2016 - Springer
This paper presents a method for reconstructing unreliable spectral components of speech
signals using the statistical distributions of the clean components. Our goal is to model the …

Classification of stop place in consonant-vowel contexts using feature extrapolation of acoustic-phonetic features in telephone speech

JW Lee, JY Choi, HG Kang - The Journal of the Acoustical Society of …, 2012 - pubs.aip.org
Knowledge-based speech recognition systems extract acoustic cues from the signal to
identify speech characteristics. For channel-deteriorated telephone speech, acoustic cues …

[PDF][PDF] Classification of Fricatives Using Feature Extrapolation of Acoustic-Phonetic Features in Telephone Speech.

JW Lee, JY Choi, HG Kang - INTERSPEECH, 2011 - isca-archive.org
This paper proposes a classification module for fricative consonants in telephone speech
using an acoustic-phonetic feature extrapolation technique. In channel-deteriorated …

[PDF][PDF] GMM-based missing-feature reconstruction on multi-frame windows

U Remes, Y Nankaku, K Tokuda - Twelfth Annual Conference of …, 2011 - isca-archive.org
Methods for missing-feature reconstruction substitute noisecorrupted features with clean-
speech estimates calculated based on reliable information found in the noisy speech signal …

[PDF][PDF] Automatic Control of Instruments Using Efficient Speech Recognition Algorithm

A Thakur, R Kumar, A Bath, J Sharma - 2014 - researchgate.net
Matlab straight forward programming interface make it an ideal tool for Hindi Key word
Recognition. For the extraction of the feature, Hindi Key word database has been designed …