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 35 for “"continuous speech"”.
-
Word posterior probabilities for large vocabulary continuous speech recognition
… posterior probabilities for large vocabulary continuous speech recognition is investigated in a unified, statistical framework. The word posterior probabilities are directly derived from the sentence posterior probabilities which are an essential part of Bayes' Decision Rule. Different …
-
Synthesis of continuous speech by concatenation of isolated words
Thesis (M.S.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1983.
-
Modeling spontaneous speech variability for large vocabulary continuous speech recognition
… techniques for improved treatment of spontaneous speech variabilities in large vocabulary automatic speech recognition are developed and evaluated on US English conversational speech and spontaneous medical dictations. Two main aspects of spontaneous speech modeling are addressed: The general …
-
Across-word phoneme models for large vocabulary continuous speech recognition
… phoneme models during large vocabulary continuous speech recognition is studied. A recognition system will be developed which allows for the training of high performance across-word phoneme models, the efficient application of these across-word phoneme models in combination with …
-
Integrate template matching and statistical modeling for continuous speech recognition
… with statistical modeling is proposed to improve continuous speech recognition. Commonly used Hidden Markov Models (HMMs) are ineffective in modeling details of speech temporal evolutions, which can be overcome by template-based methods. However, template-based methods are difficult to be extended …
-
Large vocabulary continuous speech recognition using linguistic features and constraints
Automatic speech recognition (ASR) is a process of applying constraints, as encoded in the computer system (the recognizer), to the speech signal until ambiguity is satisfactorily resolved to the extent that only one sequence of words is hypothesized. Such constraints fall naturally into two …
-
Analysis of acoustic cues for identifying consonant /ð/ in continuous speech
Thesis (M.Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2002.
-
A Novel Approach for Continuous Speech Tracking and Dynamic Time Warping. Adaptive Framing Based Continuous Speech Similarity Measure and Dynamic Time Warping using Kalman Filter and Dynamic State Model
Dynamic speech properties such as time warping, silence removal and background noise interference are the most challenging issues in continuous speech signal matching. Among all of them, the time warped speech signal matching is of great interest and has been a tough challenge for the researchers. …
-
A characterization of the problem of new, out-of-vocabulary words in continuous-speech recognition and understanding
Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1995.
-
The Effectiveness of Oral Expression through the use of Continuous Speech Recognition Technology in Supporting the Written Composition of Postsecondary Students with Learning Disabilities
… of providing a transcription service is high. Speech recognition has the potential to overcome these shortcomings, but presently little research has been conducted to investigate the advantages and disadvantages of this mode of writing. The purpose of this study was to examine the compensatory …
-
Taking attention away from the auditory modality : investigations of the effect on speech processing using machine learning
Real-world speech processing often takes place in complex multisensory environments. Listeners may need to prioritize sensory inputs from modalities other than audition. Selective attention is thought to be critical in selecting the sensory modality most relevant to the task at hand. Two critical …
-
Detection of consonant voicing : a module for a hierarchical speech recognition system
… thesis, a method for designing a hierarchical speech recognition system at the phonetic level is presented. The system employs various component modules to detect acoustic cues in the signal. These acoustic cues are used to infer values of features that describe segments. Features are …
-
Automatic Phoneme Recognition with Segmental Hidden Markov Models
A speaker independent continuous speech phoneme recognition and segmentation system is presented. We discuss the training and recognition phases of the phoneme recognition system as well as a detailed description of the integrated elements. The Hidden Markov Model (HMM) based phoneme models are …
-
An artificial Intelligence Approach to improving Speech Recognition
Speech Recognition is a technology with promising applications. However, the performance of current speech recognizers greatly limit their widespread use. Approaches to reducing the word error rate have mainly been associated with statistical techniques. As a consequence, speech recognition results …
-
Classification of vocal fold vibration as regular or irregular in normal, voiced speech
… an important communicative function in human speech and occurs allophonically in American English. This thesis uses cues from both the temporal and frequency domains - such as fundamental frequency, normalized RMS amplitude, smoothed-energy-difference amplitude (a measure of abruptness in …
-
Investigations on discriminative training criteria
… implemented for both small and large vocabulary continuous speech recognition. Special attention will be directed to the comparison and formalization of varying discriminative training criteria and corresponding optimization methods, discriminative acoustic model evaluation and feature …
-
An approach to a robust speaker recognition system
… addition, many other system components such as speech endpoint detection, automatic noise thresholds, etc. are required to build correctly in order to achieve high speaker recognition accuracy. Multi-stage decision process is used both to improve and to speed up the decision if certain criteria …
-
A log-linear discriminative modeling framework for speech recognition
Conventional speech recognition systems are based on Gaussian hidden Markov models (HMMs).Discriminative techniques such as log-linear modeling have been investigated in speech recognition only recently. This thesis establishes a log-linear modeling framework in the context of discriminative …
-
Subword-based approaches for spoken document retrieval
… items from a large collection of recorded speech messages in response to a user specified natural language text query. We investigate the use of subword unit representations for SDR as an alternative to words generated by either keyword spotting or continuous speech recognition. Our …
-
Diskriminative Modellkombination in Spracherkennungssystemen mit großem Wortschatz
… developed and implemented for large vocabulary continuous speech recognition. DMC is based on a discriminative training of the free parameters of distributions belonging to the exponential family. It is independent of the combined models and allows for the automatic combination of any set of …
Page 1 of 2