Search Results - "acoustic modelling"
-
1
-
2
Towards an accurate speaker-independent Holy Quran acoustic model
Published 2018“…In this paper, a more accurate Carnegie Melon University Sphinx acoustic model was trained for the Holy Quran chapters 001, and 067 to 114. …”
Get full text
Get full text
Get full text
-
3
Feasibility of Using Regional Seismic Reflections Surveys to Discover Iron Oxide Copper Gold (IOCG) Deposits in the Gawler Craton, South Australia
Published 2018“…By simulating surveys with acoustic modelling and comparing the simulations to real data the thesis shows this to be true. …”
Get full text
-
4
-
5
Modelling acoustic propagation beneath Antarctic sea ice using measured environmental parameters
Published 2016“…The conclusions of this work are that: (1) the accuracy of acoustic modelling in this environment is greatly increased by using realistic sound speed data; (2) a risk averse ranging model would use only the direct path signal transmission; and (3) in a flat ice scenario, much greater ranges can be achieved if the surface reflected transmission paths are included. …”
Get full text
-
6
Laser ultrasonic method for determination of crystallographic orientation of large grain metals by spatially resolved acoustic spectroscopy (SRAS)
Published 2012“…At the end of the thesis, consideration is given to further research in the acoustic modelling and data processing algorithms that would improve the technique in the future.…”
Get full text
-
7
Modelling acoustic transmission loss due to sea ice cover
Published 2013“…It outlines methods for including ice in acoustic modelling tools and demonstrates the influence of one set of ice statistics on transmission loss.…”
Get full text
Get full text
-
8
Towards using CMU Sphinx Tools for the Holy Quran recitation verification
Published 2015“…The building of the acoustic model was done using a simplified list of phonemes instead of the mainly used Romanized in order to simplify the process of training the acoustic model. …”
Get full text
Get full text
-
9
Pronunciation variations and context-dependent model to improve ASR performance for dyslexic children’s read speech
Published 2009“…Focusing on the key element for an ASR-based application for dyslexic children reading isolated words in Bahasa Melayu, this paper can be an evidence of the need to have a carefully designed acoustic model for a satisfying recognition accuracy of 79.17% on test dataset. …”
Get full text
-
10
Using Resources from a Closely-related Language to Develop ASR for a Very Under-resourced Language: A Case Study for Iban
Published 2015“…We developed a semi-supervised method for building the pronunciation dictionary and applied cross-lingual strategies for improving acoustic models trained with very limited training data. …”
Get full text
Get full text
-
11
Acoustic Pronunciation Variations Modeling for Standard Malay Speech Recognition
Published 2008“…Sound or partial changes can be handled by adjusting the acoustic models through sharing or adaptation of the Gaussian mixture components. …”
Get full text
-
12
Phonetically rich and balanced speech corpus for Arabic speaker-independent continuous automatic speech recognition systems
Published 2010“…The speech engine uses 3-emitting state Hidden Markov Models (HMM) for tri-phone based acoustic models. Based on experimental analysis of 4.07 hours of training speech data, the acoustic model used continuous observation's probability model of 16 Gaussian mixture distributions and the state distributions were tied to 400 senons. …”
Get full text
Get full text
-
13
A Framework For Automatic Code Switching Speech Recognition With Multilingual Acoustic And Pronunciation Models Adaptation
Published 2014“…We also put forward the usage of an acoustic model adaptation approach known as hybrid approach of interpolation and merging to cross-adapt acoustic models of different languages to recognize code-switching speech better. …”
Get full text
Get full text
-
14
A Framework For Automatic Code Switching Speech Recognition With Multilingual Acoustic And Pronunciation Models Adaptation
Published 2014“…We also put forward the usage of an acoustic model adaptation approach known as hybrid approach of interpolation and merging to cross-adapt acoustic models of different languages to recognize code-switching speech better. …”
Get full text
Get full text
-
15
Acoustic Speaker Localization with Strong Reverberation and Adaptive Feature Filtering with a Bayes RFS Framework
Published 2019“…Novel reverberation-robust speaker localization algorithms are derived from the signal and room acoustics models. A multi-speaker tracking filter and a multi-feature multi-speaker state filter are developed based upon the generalized labeled multi-Bernoulli random finite set framework. …”
Get full text
-
16
Arabic Speaker-Independent Continuous Automatic Speech Recognition Based on a Phonetically Rich and Balanced Speech Corpus
Published 2012“…The speech engine uses 3-emitting state Hidden Markov Models (HMM) for tri-phone based acoustic models. Based on experimental analysis of about 7 hours of training speech data, the acoustic model is best using continuous observation’s probability model of 16 Gaussian mixture distributions and the state distributions were tied to 500 senones. …”
Get full text
Get full text
Get full text
-
17
Towards using CMU sphinx tools for the Holy Quran recitation verification
Published 2016“…The building of the language model was done using a simplified list of phonemes instead of the mainly used Romanized in order to simplify the process of training the acoustic model. In this paper, the experiments resulted in Word Error Rates (WER) as low as 1.5% even with a very small set of audio files used during the training phase.…”
Get full text
Get full text
-
18
Application of the fast multipole boundary element method to underwater acoustic scattering.
Published 2011“…A possible method for coupling an exterior acoustic model to a structural model, both calculated via the FMA, is outlined here. …”
Get full text
-
19
Analysis of Malay Speech Recognition for Different Speaker Origins
Published 2012“…We employ context dependent models by applying linear discriminant analysis for our acoustic model and a trigram based language model. Our experiments show improved results when linear discriminant analysis technique was employed in our model while our recognizer performed worst for speakers with accent that are not available in the training data.…”
Get full text
-
20
FMBEM analysis of sound scattering from a damping plate in the near field of a hydrophone.
Published 2012“…As part of research into the effect of underwater noise on the communication between an under-ice Autonomous Underwater Vehicle (AUV) and it’s stationary launch vessel (the Aurora Australis), fast multipole boundary element method (FMBEM) acoustic modeling was conducted. In particular, a steel damping plate with a complex 3-dimensional structure was modeled (using up to 1.6 x 10 5 boundary elements) and the effect of sound scattering from a pinger near the ship was determined at the receiver hydrophone, which was in close proximity to the damping plate. …”
Get full text
Get full text