Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 53 for “"acoustic model"”.
-
Acoustic model adaptation for recognition of dysarthric speech
Item reinstated by Sarah Shreeves (sshreeve@illinois.edu) on 2014-06-28T10:00:22Z Item was in collections: Dissertations and Theses - Electrical and Computer Engineering (ID: 446) Graduate Theses and Dissertations at Illinois (ID: 204) No. of bitstreams: 2 Sharma_Harsh.pdf: 1379121 bytes, checksum: …
-
Acoustic Model Adaptation For Reverberation Robust Automatic Speech Recognition
… adaptation" technique which adapts the clean acoustic models to the reverberant environment and thus provide improved performance. Semi-blind adaptation technique works in two phases, in the first phase reverberation model is estimated and in the second phase using the reverberation model, …
-
Flow -Induced Noise in Heat Exchangers
… inside a rectangular duct have been made. The acoustic field in parts of the duct in which travelling hydrodynamic pressure fluctuations produced by vortex shedding do not contaminate the results was investigated by measuring sound pressure levels. Many of the results are believed to be unique. …
-
Acoustic models of consonant recognition in cochlear implant users
… made by normal-hearing subjects listening to acoustic models of implant processing, in various conditions. Two initial experiments were undertaken to develop and refine an acoustic model of the Nucleus 24 cochlear implant. Findings from these two experiments informed the design of the main …
-
Discriminative and adaptive training for robust speech recognition and understanding
… bi-directional long short-term memory (BLSTM) acoustic models is proposed to minimize the recognition errors of only the keywords. (2) To compensate for the mismatched objectives of speech recognition and understanding, minimum semantic error cost training of the BLSTM acoustic model is …
-
Pronunciation modeling for large vocabulary speech recognition
… speech recognition (ASR). Many pronunciation modeling approaches have been developed to address this problem. Some explicitly manipulate the pronunciation dictionary as well as the set of the units used to define the pronunciations of words. Other approaches model the pronunciation implicitly …
-
Automatic Speech Recognition Quality Estimation
… hypotheses scenario. In the former, a regression model is used to predict the WER score of each single hypothesis that is created through a single automatic transcription channel. In the latter, a ranking model is used to predict the order of multiple hypotheses with respect to their quality. …
-
Speech Representation Models for Speech Synthesis and Multimodal Speech Recognition
… phones today. In this thesis, I apply speech modeling techniques developed for recognition to two other speech problems: speech synthesis and multimodal speech recognition with images. In both problems, there is a need to learn a relationship between speech sounds and another source of …
-
Pronunciation learning for automatic speech recognition
… speech recognizers (ASRs). Unlike stochastic acoustic and language models that learn the values of their parameters from training data, the baseform pronunciations of words in an ASR vocabulary are typically specified manually, and do not change, unless they are edited by an expert. Our work …
-
Combining Speech with textual methods for arabic diacritization
… weighted combination of speech with a text-based model is used to allow linguistically-insensitive acoustic information to correct and complement the errors generated by the text model's diacritic predictions. The acoustic model is based on Hidden Markov Models and the textual model on Conditional …
-
Joint Training Methods for Tandem and Hybrid Speech Recognition Systems using Deep Neural Networks
Hidden Markov models (HMMs) have been the mainstream acoustic modelling approach for state-of-the-art automatic speech recognition (ASR) systems over the past few decades. Recently, due to the rapid development of deep learning technologies, deep neural networks (DNNs) have become an essential part …
-
Nasal codas in Standard Chinese : a study in the framework of the distinctive feature theory
… (SC) are compared to distinguish between the acoustic correlates of language-universal distinctive features and language-specific enhancing attributes. The distinctive feature theory and the theory of enhancement provide a framework for quantifying the acoustic and articulatory patterns …
-
Acoustic Transfer Functions Derived from Finite Element Modeling for Thermoacoustic Stability Predictions of Gas Turbine Engines
Acoustic Transfer Functions Derived from Finite Element Modeling for Thermoacoustic Stability Predictions of Gas Turbine Engines Design and prediction of thermoacoustic instabilities is a major challenge in aerospace propulsion and the operation of power generating gas turbine engines. This is a …
-
Acoustic event, spoken keyword and emotional outburst detection
… describes a system for large-scale multi-label acoustic event detection (AED) in YouTube videos. It explores the potential of the state-of-the-art deep learning classifiers for AED, describes both qualitative and quantitative results (Hit@1 is 47.9%) and presents the pre-trained embedding model …
-
The benefits of acoustic perceptual information for speech processing systems
… theories such as auditory roughness and acoustic landmarks can act as heuristics to these systems and benefit them in multiple ways. Findings of acoustic landmarks hint that the idea of treating each frame equally might not be optimal. In some cases, landmark information can improve …
-
Development of Reduced-Order Flame Models for Prediction of Combustion Instability
… gas turbines, but it is susceptible to thermoacoustic instabilities, which can result in large amplitude pressure oscillations in the combustion chamber. The thermoacoustic limit cycle is generated by the unsteady heat release dynamics coupled to the combustor acoustics. In this dissertation, …
-
Crossing the Air-Water Interface: Inspiration from Nature
… and their resulting force after pinch-off. An acoustic model predicts the observed wavelengths of the ripples. The final topic will delve into the mechanics of how animals leap out of water. A scaling law that balances the power of thrust and drag will predict the height of the jump. Finally, a …
-
Parts-based models and local features for automatic speech recognition
… conditions. This thesis revisits the basic acoustic modeling assumptions common to most ASR systems and argues that improvements to the underlying model of speech are required to address these shortcomings. A number of problems with the standard method of hidden Markov models (HMMs) and …
-
Multi-modal and deep learning for robust speech recognition
… present. In this thesis, speech denoising and model adaptation for robust speech recognition were studied, and four novel methods were introduced to improve ASR robustness. First, we developed an ASR system using multi-channel information from microphone arrays via accurate speaker tracking …
-
Identification of Thermoacoustic Dynamics Exhibiting Limit Cycle Behavior
Identification of thermoacoustic dynamics that exhibit limit cycle behavior is needed to gain a better intuitive feel of the system, to design complex control strategies, and to validate modeling efforts. Limit cycle oscillations arise in thermoacoustic systems due to the coupling between a …
Page 1 of 3