Communication Sciences and Disorders Commons^™

Gaussian Mixture Models And Neural Networks For Automatic Speaker Identification, Usha Gayatri Chalkapally

Electrical & Computer Engineering Theses & Dissertations

Automatic Speaker Recognition is the process of automatically recognizing who is speaking on the basis of individual information contained in speech signals. This technique of Automatic Speaker Recognition makes it possible to use the speaker's voice to verify their identity and control access to services such as voice dialing, banking by telephone, telephone shopping, database access services, information services, voice mail, security control for confidential information areas, and remote access to computers.

In this thesis, the techniques of Gaussian Mixture Models and Neural Networks for Automatic Speaker Identification are presented. Algorithms for Speaker Identification using Gaussian Mixture Models were developed, …

Effects Of Gesture+Verbal Treatment For Noun And Verb Retrieval In Aphasia, Anastasia M. Raymer, Floris Singletary, Amy Rodriguez, Maribel Ciampitti, Kenneth M. Heilman, Leslie J. Gonzalez Rothi

Communication Disorders & Special Education Faculty Publications

Links between verbs and gesture knowledge suggest that verb retrieval may be particularly amenable to gesture+verbal training (GVT) in aphasia compared to noun retrieval. This study examines effects of GVT for noun and verb retrieval in nine individuals with aphasia subsequent to left hemisphere stroke. Participants presented an array of noun and verb retrieval deficits, including impairments of semantic and/or phonologic processing. In a single-participant experimental design, we investigated effects of GVT for noun and verb retrieval in two counterbalanced treatment phases. Effects were evaluated in spoken naming and gesture production to pictured objects and actions. Spoken naming improvements associated …

Word-Retrieval Treatment In Aphasia: Effects Of Sentence Context, Anastasia Raymer, Francine Kohen

Communication Disorders & Special Education Faculty Publications

Word-retrieval treatment studies in aphasia have reported the greatest influences on picture naming for trained words. To increase treatment effects to untrained words and sentence contexts, we investigated a sentence-reading treatment hierarchy that moves from errorless to generative production of sentences incorporating target nouns and verbs. In an individual with nonfluent aphasia, treatment resulted in improved picture naming for nouns and verbs and generalized increases in numbers of grammatical sentences and content words following noun therapy. A second individual with fluent aphasia improved little in picture-naming and sentence-generation tasks for both nouns and verbs. This sentence-based word-retrieval training, in which …

Perspectives On Attention Deficit Hyperactivity Disorder: Executive Functions, Working Memory, And Language Disabilities, Carol Westby, Silvana Watson

Communication Disorders & Special Education Faculty Publications

The conceptualization of the nature of attention deficit hyper-activity disorder (ADHD) has changed in the last decade. ADHD is now viewed as a neurologically based condition with primary deficits in executive functions and working memory (WM). Students with ADHD have deficits in discourse organization, inferring, and monitoring that are related to their executive function and WM deficits. A large number of students with ADHD also have comorbid reading and language disabilities that exist in addition to the deficits directly associated with the ADHD. Comprehensive evaluation of students with ADHD is essential to address their specific learning needs

A Computer-Based Articulation Training Aid For Short Words (Cata), Mukund Devarajan

Electrical & Computer Engineering Theses & Dissertations

Several improvements in the vowel articulation training aid (VATA) are described, as well as the efforts to extend the visual feedback system to operate with short words in the form of consonant, vowel and consonant (CVC). The extended version of the visual feedback system is referred to as CATA (Computer-based Articulation Training Aid); the vowel version of the aid (VATA) only operates with ten American English monopthong vowels. Improvements in VATA include the use of a neural network (NN) recognizer method to prune a large database of vowel recordings to eliminate noisy and/or mispronounced tokens. The spectral jitter problem, previously …

Automatic Speaker Identification Using Reusable And Retrainable Binary-Pair Partitioned Neural Networks, Ashutosh Mishra

Electrical & Computer Engineering Theses & Dissertations

This thesis presents an extension of the work previously done on speaker identification using Binary Pair Partitioned (BPP) neural networks. In the previous work, a separate network was used for each pair of speakers in the speaker population. Although the basic BPP approach did perform well and had a simple underlying algorithm, it had the obvious disadvantage of requiring an extremely large number of networks for speaker identification with large speaker populations. It also requires training of networks proportional to the square of the number of speakers under consideration, leading to a very large number of networks to be trained …

Treatment Of Adynamia In Aphasia, Anastasia M. Raymer

Communication Disorders & Special Education Faculty Publications

Transcortical motor aphasia (TCMA) is an acquired impairment of language expression that occurs following neurologic damage that affects left frontal cortex and spares perisylvian regions. In some individuals with TCMA, verbal expression is rendered nonfluent due to difficulty spontaneously initiating and elaborating upon verbal messages. Nonfluency arises from impaired activation of intended messages and inhibition of competing verbal expressions. This impairment of the intentional aspects of language expression can be termed 'adynamia.' Because adynamic forms of TCMA occur infrequently, few systematic treatment investigations have been reported for this condition. Behavioral treatments have been proposed to engage intact frontal regions to …

Yet Another Algorithm For Pitch Tracking (Yaapt), Kavita Kasi

Electrical & Computer Engineering Theses & Dissertations

This thesis presents a pitch detection algorithm that is extremely robust for both high quality and telephone speech. The kernel method for this algorithm is the Normalized Cross Correlation (NCCF) reported by David Talkin [16]. Major innovations include: processing of the original acoustic signal and a nonlinearly processed version of the signal to partially restore very weak F0 components; intelligent peak picking to select multiple F0 candidates and assign merit factors; and, incorporation of highly robust pitch contours obtained from smoothed versions of low frequency portions of spectrograms. Dynamic programming is used to find the ''best" pitch track among all …

Effects Of Occupational Ultrasonic Noise Exposure On Hearing Of Dental Hygienists: A Pilot Study, Jennifer Dunning Wilson, Michele Leonardi Darby, Susan L. Tolle, Joseph C. Sever Jr.

Dental Hygiene Faculty Publications

Purpose. The purpose of this case-control study was to determine whether long-term ultrasonic noise exposure via the dental office environment is related to dental hygienists' hearing status.

Methods. Registered dental hygienists (N - 698) who live in the Hampon Roads areas of Virginia were mailed a Dental Hygiene Word History Questionnaire to determine who would meet the inclusion criteria and would be willing to participate in the study. Consenting subjects were categorized into one of two groups, according to ultrasonic sealer usage rate, and matched on age. Persons with known hearing loss due to infection, disease, or congenital defect were …

The Effects Of Occupational Ultrasonic Noise Exposure On Hearing In Dental Hygienists: A Pilot Study, Jennifer S. Dunning

Dental Hygiene Theses & Dissertations

The purpose of this case-control study was to determine whether long-term ultrasonic noise exposure via the dental office environment is related to dental hygienists' hearing status. Registered dental hygienists (N = 698) who live in the Hampton Roads area were mailed a Dental Hygiene Work History Questionnaireto determine those meeting the inclusion criteria and willing to participate in the study. Consenting subjects were categorized into one of two groups according to ultrasonic scaler usage rate and matched on age. Persons with known hearing loss due to infection, disease, or congenital defect were excluded from the study. The final sample …

Minimum Mean Square Error Spectral Peak Envelope Estimation For Automatic Vowel Classification, Jaishree Venugopal

Electrical & Computer Engineering Theses & Dissertations

Spectral feature computations continue to be a very difficult problem for accurate machine recognition of speech. In this work, which focuses on vowels, a new spectral peak envelope method for vowel classification is developed, based on a missing frequency components model of speech recognition. According to the missing frequency components model, vowel recognition depends only on the spectral (harmonic) peaks. Smoothing and interpolation of the spectra, performed in the standard cepstral analysis method commonly used in automatic speech recognition, actually loses valuable information and results in reduced recognition accuracy. The new method for feature extraction presented in this thesis is …

Signal Modeling With Non-Uniform Time Sampling Of Features For Automatic Speech Recognition, Montri Karnjanadecha

Electrical & Computer Engineering Theses & Dissertations

This dissertation presents an investigation of non-uniform time sampling methods for spectral/temporal feature extraction in speech. Frame-based features were computed based on an encoding of the global spectral shape using a Discrete Cosine Transform. In most current “standard” methods, trajectory (dynamic) features are determined from frame-based parameters using a fixed time sampling, i.e., fixed block length and fixed block spacing. In this research, new methods are proposed and investigated in which block length and/or block spacing are variable. The idea was initially tested with HMM-based isolated word recognition, and a significant performance improvement resulted when a variable block length and …

Variability Analysis Of Discrete Cosine Transform Coefficient (Dctc) Features For Speech Processing, Bingjun Dai

Electrical & Computer Engineering Theses & Dissertations

In this research, the variability of Discrete Cosine Transform Coefficient (DCTC) features was investigated. Additionally, a new pitch-synchronous processing method was explored to increase the stability of features and to reduce window effects when compared to the regular method. The noise sources that lead to feature variability were analyzed, and different smoothing methods were tested. It was found that longer frames, frequency warping, time smoothing of the log spectrum, and DCS level time smoothing, all help reduce DCTC variability and increase classification performance. The pitch­ synchronous method was implemented with Matlab. Important processing methods, including pitch period estimation, time­ domain …

Real-Time Visual Speech Articulation Training Aid, Neiyer S. Correal

Electrical & Computer Engineering Theses & Dissertations

A real-time visual articulation training aid has been implemented. It provides instantaneous visual feedback of vowel and stop-consonant production on a computer screen. The vowel training system corresponds to an improved floating-point implementation of a previous fixed-point system developed by Beck (1992). The new implementation provides better accuracy and an approximate five-fold increase in speed. Acoustic features computed from global short-time spectral shape are used for classification of vowels. Temporal spectral trajectories timed to begin with burst onset are used for stop consonants. A neural network is used to transform measurements of auditory stimuli from the feature space to a …

Text Independent Speaker Verification Using Binary-Pair Partitioned Neural Networks, Claude A. Norton Iii

Electrical & Computer Engineering Theses & Dissertations

A method is presented for the application of binary-pair partitioned neural networks to the task of speaker verification. This technique is based on a previously developed neural network classifier for speaker identification.

The main focus of this research was the development and testing of the algorithms necessary to extend the binary-pair partitioning approach from speaker identification to speaker verification. The method is based on the development of a user profile which is obtained from discriminative data provided by the binary-pair partitioned neural networks.

Experimental results are provided which demonstrate the viability of this approach, using the TIMIT speech corpus for …

Formant Estimation From Dctc's Using A Feedforward Neural Network, Shubhangi U. Kelkar

Electrical & Computer Engineering Theses & Dissertations

Formants are the natural frequencies of the human vocal tract. Existing methods for estimating formants from speech signals are computationally complex and subject to errors for certain type of speech sounds. This thesis describes a method for estimating vowel formant frequencies from Discrete Cosine Transform Coefficients (DCTC's), a form of cepstral coefficients, using a feedforward neural network with back-propagation training. Experimental results are based on a large multispeaker data base. The results are obtained for both a linear transformation and a feedforward neural network with a nonlinear hidden layer. In general, the neural network transformation is superior to the linear …

Visual Speech Training Aid For The Deaf, Subhashri Venkat

Electrical & Computer Engineering Theses & Dissertations

A computer-based vowel articulation training aid has been developed. A "continuous" acoustic-phonetic transformation is performed to map speech parameters to a lower dimensionality display space. There are two possible approaches to this transformation problem. The transformation could be either linear or a combination nonlinear/linear. The nonlinear transformation is performed using a multi-layered feedforward neural network with linear output layers. Speech parameters are extracted either from an analog filter bank arrangement (band energies) or by a digital signal processing procedure (Discrete Cosine Transform Coefficients). The speech parameters obtained from both methods correspond to the spectral envelope of the speech signals. The …

An Investigation To Improve Linear Predictive Vocoder Pulse/Noise Excitation Models, Elizabeth Annella Martina Effer

Electrical & Computer Engineering Theses & Dissertations

The quality of synthetic speech from Linear Predictive (LP) vocoders is known to be degraded due to the lack of detail in the commonly used pulse/noise excitation model. In this investigation, it was hypothesized that this degradation is due to the lack of precise timing information in the pulses and to the constraint that each short-time segment of excitation be either an impulse train or white noise. Accordingly, more complex excitation models were implemented using precise timing from peaks in the residual and a mixture of pulses and noise. Since the LP residual is known to be the perfect excitation …

Color Display Of Vowel Spectra As A Training Aid For The Deaf, Amir Jalali Jagharghi

Electrical & Computer Engineering Theses & Dissertations

The objective of this research was to develop a transformation for mapping speech parameters to color parameter. This transformation is done in real-time, and the resulting color parameter are continuously displayed on a color monitor. This visual speech display is to be used as a speech articulation training aid for the deaf. The conversion of speech acoustic signals into speech parameter was accomplished using special -purpose electronics. The real-time conversion of speech parameter to display parameter was controlled by an 8086/8088 microprocessor operating in an S-100 bus structure. The coefficients of the Karhunen-Loeve series expansion of speech power spectra were …

Block Encoding Of Speech Spectral Principal Components, James R. Holland Jr.

Electrical & Computer Engineering Theses & Dissertations

A Karhunen-Loeve series expansion was used to block encode speech spectral principal components as a function of time. Each of ten principal components was first obtained as a linear combination of 2© speech spectral band energies. Using a fixed block length of 10 frames (0.128 s), the K-L basis vectors were computed separately for various speakers for each principal component. In all cases the resulting basis vectors were essentially a set of discrete cosine basis vectors. Synthesis of speech from the block encoded parameters showed that very little information is lost with up to 70% data reduction. The block encoding …

Narrow Band Modification For Speech Testing Of The Cochlear Reserve By Threshold Shift, Michael F. Seidemann

Communication Disorders & Special Education Theses & Dissertations

No abstract.