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 19 of 19 for “"speech features"”.
-
Thin slices of interest
… an automatic human interest detector that uses speech, physiology, body movement, location and proximity information. The speech features, consisting of activity, stress, empathy and engagement measures are used in three large experimental evaluations; measuring interest in short conversations, …
-
Toward a social signaling framework : activity and emphasis in speech
… pitch, speaking rate, and other non-linguistic speech features are crucial aspects of human spoken interaction. In this thesis, we separate these speech features into two categories -- vocal Activity and vocal Emphasis -- and propose a framework for classifying high-level social behavior …
-
Neural speech tracking in quiet and noisy listening environments using naturalistic stimuli
In noisy situations, speech may be masked with conflicting acoustics, including background noise from the environment or other competing talkers. The process of listening to one stream of sounds while ignoring background noise is referred to as the “cocktail party problem,” but its physiological …
-
Model-Based Speech Enhancement
Abstract A method of speech enhancement is developed that reconstructs clean speech from a set of acoustic features using a harmonic plus noise model of speech. This is a significant departure from traditional filtering-based methods of speech enhancement. A major challenge with this approach is to …
-
Real-time noise-robust speech detection
… noise-robust techniques towards real-time speech detection in real environments. Dynamic noises in the environment (including motor noise, babble noise, and other noises in a warehouse setting) can dramatically alter the speech signal, making speech detection much more difficult. In …
-
Selective attention for audiovisual integration of speech
… the audiovisual world into a set of audiovisual features such as color, shape, and pitch. An important question in perception science is whether selective attention is required to bind audiovisual features back into unified perceptual objects. In visual displays, targets defined as conjunctions …
-
Exploration of small enrollment speaker verification on handheld devices
… the impact of a number of key factors, such as speech features, basic modeling techniques, as well as highly variable environmental/microphone conditions on speaker verification accuracy. We then present and evaluate methods for improving speaker verification robustness. In particular, we focus …
-
Productivity Measurement of Call Centre Agents using a Multimodal Classification Approach
… approach to model the recorded calls as text and speech. It is based on the following: 1) focus on the technical part of agent performance, 2) objective evaluation of the corpus, 3) extension of features for both text and speech, and 4) combination of the best accuracy from text and speech data …
-
Removing redundancy in speech by modeling forward masking
… approaches to this, the first being automatic speech recognition (ASR). Even though many state-of-the-art analysis methods, such as LPC, STFT, and MFCC, have been used in speech recognition, the performance of ASR has reached a plateau and the speech decoding problem remains unresolved. …
-
Adaptation of hybrid deep neural network-hidden Markov model speech recognition system using a sub-space approach
The performance of automatic speech recognition (ASR) system can be enhanced by adaptation of the ASR for a particular speaker or a group of speakers. In ASR, training and testing data often do not follow the same statistics; they are often mismatched, which leads to a gap in performance. The …
-
The application of linear and nonlinear estimators of acoustic variability in the assessment of speech motor control in hypokinetic dysarthria
… measures in the assessment and treatment of speech disorders, researchers and clinicians are always in search of new techniques to quantify speech impairment. This thesis investigates the relatively unexplored area of linear and nonlinear estimators of acoustic variability and their …
-
Verification of feature regions for stops and fricatives in natural speech
… of acoustic cues and their importance in speech perception have long remained debatable topics. In spite of several studies that exist in this eld, very little is known about what exactly humans perceive in speech. This research takes a novel approach towards understanding speech …
-
Leveraging Subtle Verbalization and Speech Patterns to Help Evaluators Identify Usability Problem Encounters in Concurrent Think-aloud Sessions
… subtle patterns in users’ verbalizations and speech when they encounter problems in think-aloud sessions and further leverage these patterns to support the analysis of think-aloud sessions. In this dissertation, I first survey user experience (UX) practitioners around the world to understand …
-
Exploring Perceptions of Second Language Speech Fluency Through Developing and Piloting a Rating Scale for a Paired Conversational Task
Much research has explored how perceptions of speech fluency are influenced by a variety of temporal speech features (e.g. speech rate). However, less is known about the influence of non-temporal and conversational speech characteristics, as well as listener characteristics such as accent …
-
Perception of prosody by cochlear implant recipients
… implants (CIs) display remarkable success with speech recognition in quiet, but not with speech recognition in noise. Normal-hearing (NH) listeners, in contrast, perform relatively well with speech recognition in noise. Understanding which speech features support successful perception in noise …
-
A cross-linguistic study of certain temporal features of speech in stuttering and nonstuttering children
… performed to measure temporal coarticulatory speech features in the perceptually fluent speech of 120 South African children. The aim was to test, in a limited way, the postulate that stuttering may be essentially a disorder of speech timing. Comparisons were made between English- and …
-
Acoustic-based assistive technology tools for dysarthria managment
… treatment of dysarthria, a neurological motor speech disorder. The novel algorithms presented in this thesis include a silence, unvoiced and voiced segmentation technique for dysarthric speech based on linear prediction error variance (LPEV), an automatic diadochokinetic (DDK) analysis and …
-
Investigating speech technology for monitoring disease progression in the context of neurodegenerative disease
… of artificial intelligence (AI), particularly speech analysis, natural language processing and machine learning, offers opportunities for the automatic analysis of spoken language data. The work presented in this thesis applies an AI approach to the context of dementia, addressing three …
-
Αναγνώριση ομιλητή και ομιλίας με χρήση κυματιδίων
Σκοπός της παρούσας διατριβής είναι η εκμετάλλευση των κυματιδίων με σκοπό την βελτίωση της απόδοσης συστημάτων αναγνώρισης ομιλητή και ομιλίας. Στα πλαίσια αυτά, εισάγονται τέσσερις νέοι τρόποι παραμετροποίησης του σήματος ομιλίας: (1) Η πρώτη μέθοδος προσαρμόζει την ανάλυση συχνότητας των πακέτων …