國立虎尾科技大學 |

Enabling EMG-Based Silent Speech Transcription Through Speech-To-Text Transfer Learning

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Enabling EMG-Based Silent Speech Transcription Through Speech-To-Text Transfer Learning/ Alexander Garcia.
作者:	Garcia, Alexander,
面頁冊數:	1 electronic resource (96 pages)
附註:	Source: Masters Abstracts International, Volume: 86-05.
Contained By:	Masters Abstracts International86-05.
標題:	Neural networks. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31691900
ISBN:	9798346392163

Enabling EMG-Based Silent Speech Transcription Through Speech-To-Text Transfer Learning
Garcia, Alexander,

Enabling EMG-Based Silent Speech Transcription Through Speech-To-Text Transfer Learning [electronic resource] /Alexander Garcia. - 1 electronic resource (96 pages)

Source: Masters Abstracts International, Volume: 86-05.

In recent years, advances in deep learning have allowed various forms of electrographic signals, such as electroencephalography (EEG) and electromyography (EMG), to be used as a viable form of input in artificial intelligence applications, particularly for applications in the medical field. One such topic that EMG inputs have been used is in silent speech interfaces, or devices capable of processing speech without an audio-based input. The goal of this thesis is to explore a novel method of training a machine learning model to be used for silent speech interface development: using transfer learning to leverage a pre-trained speech recognition model for classifying EMG-based silent speech inputs.To accomplish this, we pass labeled EMG data through a custom transformation process, turning the data into musical notes that represent changes in an EMG sensor as silent speech data is captured. This transformed data was used as input into a pre-trained speech recognition model, and the model's classification layers were retrained to better fit the incoming data. The custom transformation process and model demonstrated progress towards effective classification with a small, closed-vocabulary dataset but showed no signs of effective training with a larger, open-vocabulary dataset. The effectiveness on the small closed-vocabulary dataset demonstrate that training a model to recognize EMG data using transfer learning on a pre-trained speech to text model is a viable approach.

English

ISBN: 9798346392163Subjects--Topical Terms:

1011215
Neural networks.

Enabling EMG-Based Silent Speech Transcription Through Speech-To-Text Transfer Learning
LDR:02805nam a22003613i 4500 001 1172899
005 20260622113222.5
006 m o d
007 cr|nu||||||||
008 260803s2024 miu||||||m |||||||eng d
020 $a 9798346392163
035 $a (MiAaPQD)AAI31691900
035 $a (MiAaPQD)CalPoly4562
035 $a AAI31691900
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Garcia, Alexander, $e author. $3 1503531
245 1 0 $a Enabling EMG-Based Silent Speech Transcription Through Speech-To-Text Transfer Learning $c Alexander Garcia. $h [electronic resource] /
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (96 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 86-05.
500 $a Advisors: Kurfess, Franz Committee members: Pantoja, Maria; Khosmood, Foaad.
502 $b M.S. $c California Polytechnic State University $d 2024.
520 # $a In recent years, advances in deep learning have allowed various forms of electrographic signals, such as electroencephalography (EEG) and electromyography (EMG), to be used as a viable form of input in artificial intelligence applications, particularly for applications in the medical field. One such topic that EMG inputs have been used is in silent speech interfaces, or devices capable of processing speech without an audio-based input. The goal of this thesis is to explore a novel method of training a machine learning model to be used for silent speech interface development: using transfer learning to leverage a pre-trained speech recognition model for classifying EMG-based silent speech inputs.To accomplish this, we pass labeled EMG data through a custom transformation process, turning the data into musical notes that represent changes in an EMG sensor as silent speech data is captured. This transformed data was used as input into a pre-trained speech recognition model, and the model's classification layers were retrained to better fit the incoming data. The custom transformation process and model demonstrated progress towards effective classification with a small, closed-vocabulary dataset but showed no signs of effective training with a larger, open-vocabulary dataset. The effectiveness on the small closed-vocabulary dataset demonstrate that training a model to recognize EMG data using transfer learning on a pre-trained speech to text model is a viable approach.
546 $a English
590 $a School code: 2104
650 # 4 $a Neural networks. $3 1011215
690 $a 0800
710 2 # $a California Polytechnic State University. $3 1437733
720 1 $a Kurfess, Franz $e degree supervisor.
773 0 # $t Masters Abstracts International $g 86-05.
790 $a 2104
791 $a M.S.
792 $a 2024
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31691900