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 205 for “"ASR"”.
-
ASR dependent techniques for speaker recognition
Thesis (M.Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2002.
-
Analyzing Icelandic conversation using State-of-the-Art ASR models
… transformer-based Automatic Speech Recognition (ASR) systems applied to Icelandic conversational speech, with a primary focus on OpenAI’s Whisper model and a secondary fo- cus on Meta’s Wav2Vec 2.0. The study uses the Spjallrómur dataset, a 21-hour unscripted dialogue dataset between two speakers …
-
Self-supervision strategies for post-ASR error correction in clinical domain.
… and inefficiency. Automatic Speech Recognition (ASR) systems offer a promising solution by transcribing spoken language into written text, enabling clinicians to dictate notes in real-time. However, using ASR systems in medical environments remains challenging due to the need for high accuracy in …
-
The effects of ASR-based practice on learners’ perception of L2 sounds
… effectiveness of automatic speech recognition (ASR) tools, such as Google Translate (GT), in supporting second language pronunciation learning, most existing studies focus on learners’ production gains in self-directed settings. No research has been found investigating whether ASR-mediated …
-
Semi-supervised cycle-consistency training for end-to-end ASR using unpaired speech
… train end-to-end automatic speech recognition (ASR) models using unpaired speech. In general, large amounts of paired data (speech and text) are needed to train an end-to-end automatic speech recognition system. To alleviate the problem of limited paired data, the idea of cycle-consistency …
-
SegmentPerturb: effective black-box hidden voice attack on commercial ASR systems via selective deletion
Voice control systems continue becoming more pervasive as they are deployed in mobile phones, smart home devices, automobiles, etc. Commonly, voice control systems have high privileges on the device, such as making a call or placing an order. However, at the same time, they are vulnerable to voice …
-
Mitigation and Evaluation of Alkali-Silica Reaction (ASR) and Freezing and Thawing in Concrete Transportation Structures
<p>An evaluation of alkali-silica reaction (ASR) and freezing and thawing (F/T) in concrete transportation structures is presented along with mitigation methods for slowing the rate of deterioration in concrete. A combination of field and laboratory testing confirms ASR deterioration is exacerbated …
-
A parametric study of the stress distribution in a four-celled box beam model of the ASR-21 Class Catamaran cross-structure.
Thesis: Ocean E., Massachusetts Institute of Technology, Department of Ocean Engineering, 1972
-
Identifying Damage, Predicting Expansion, and Determining the Effectiveness of Sealers on Concrete Affected by Alkali-Silica Reaction and Freeze-Thaw
… due to a combination of Alkali-Silica Reaction (ASR) and freeze-thaw has led to ASR and freeze-thaw research at the University of Arkansas. Potential for further expansion (PFET), Damage Rating Index (DRI), and mitigation of freeze-thaw and ASR with sealers testing and results are contained …
-
Evaluation of the usability and usefulness of automatic speech recognition among users in South Africa
An automatic speech recognition (ASR) system is a software application which recognizes human speech, processes it as input, and displays a text version of the speech as output or uses the input as commands for another application's usage. ASR can either be speaker-dependent or speaker-independent. …
-
The Use of Speech Recognition Technology in Automotive Applications
… examine automatic speech recognition (ASR) design parameters, input modalities, and driver ages; and (4) to provide human factors recommendations for the use of speech recognition technology in automotive applications. Two experiments were conducted to determine the effects of ASR …
-
Neural Time Alignment for End-to-End Automatic Speech Recognition Systems
Automatic Speech Recognition (ASR) is an important component for machines to interact with humans. With the development of deep learning, ASR systems can obtain very low error rates when there is a lot of training data available. Apart from the recognised text, it is also important to determine …
-
Automatic Speech Recognition Quality Estimation
Evaluation of automatic speech recognition (ASR) systems is difficult and costly, since it requires manual transcriptions. This evaluation is usually done by computing word error rate (WER) that is the most popular metric in ASR community. Such computation is doable only if the manual references …
-
Human and automatic speech recognition in the presence of speech-intrinsic variations
… und Verbesserung automatischer Spracherkennung (ASR). Da das menschliche auditorische System heutigen ASR-System weit überlegen ist, wurde zunächst die Erkennungsleistung von Mensch und Maschine verglichen. Aus den spezifischen Unterschieden wurden Rückschlüsse auf Signalverarbeitungsmechanismen …
-
Evaluation of the usability and usefulness of automatic speech recognition among users in South Africa [electronic resource]
An automatic speech recognition (ASR) system is a software application which recognizes human speech, processes it as input, and displays a text version of the speech as output or uses the input as commands for another application’s usage. ASR can either be speaker-dependent or speakerindependent. …
-
Characterization, Evaluation, And Repair of Full-Scale Alkali-Silica Reaction Affected Structural Concrete
Alkali–silica reaction (ASR), a chemical reaction occurring in concrete between reactive siliceous minerals in some aggregates and alkalis in the concrete pore solution, can produce an expansive gel that, in the presence of sufficient moisture, leads to expansion and cracking. This not only …
-
Effective automatic speech recognition data collection for under–resourced languages
… role in developing automatic speech recognition (ASR) technologies for such languages, a key step in developing these technologies is the effective collection of ASR data, consisting of transcribed audio and associated meta data. The problem is that no suitable tool currently exists for …
Page 1 of 11