Speech Recognition
-
Upload
hugo-moreno -
Category
Education
-
view
2.175 -
download
3
description
Transcript of Speech Recognition
![Page 1: Speech Recognition](https://reader035.fdocuments.us/reader035/viewer/2022081413/547d699db4af9fa2088b45d4/html5/thumbnails/1.jpg)
Speech Recognition for Control
Hugo MorenoESPOCH-ECUADOR
IEEE Member
![Page 2: Speech Recognition](https://reader035.fdocuments.us/reader035/viewer/2022081413/547d699db4af9fa2088b45d4/html5/thumbnails/2.jpg)
AGENDA
Introduction Speech Recognition Application in Control Conclusions
![Page 3: Speech Recognition](https://reader035.fdocuments.us/reader035/viewer/2022081413/547d699db4af9fa2088b45d4/html5/thumbnails/3.jpg)
Introduction
![Page 4: Speech Recognition](https://reader035.fdocuments.us/reader035/viewer/2022081413/547d699db4af9fa2088b45d4/html5/thumbnails/4.jpg)
Introduction
VISION
To be a leading institution in the Top Education and in the scientific and technological support for the socioeconomic and cultural development of the province of Chimborazo and of the country, with quality, relevancy and social recognition
![Page 5: Speech Recognition](https://reader035.fdocuments.us/reader035/viewer/2022081413/547d699db4af9fa2088b45d4/html5/thumbnails/5.jpg)
Speech Recognition
speaker recognition recognizing who is speaking frequencies
speech recognition recognizing what is being said
accuracy and speed
![Page 6: Speech Recognition](https://reader035.fdocuments.us/reader035/viewer/2022081413/547d699db4af9fa2088b45d4/html5/thumbnails/6.jpg)
Speech Recognition The process of converting a speech signal to a sequence of
words in the form of digital data or discrete data, by means of an algorithm implemented as a computer program
(microcontroller).
![Page 7: Speech Recognition](https://reader035.fdocuments.us/reader035/viewer/2022081413/547d699db4af9fa2088b45d4/html5/thumbnails/7.jpg)
Speech Recognition Speech Signal Acquisition
LPF – AB = 4KHz 8Ks/s 8-16 bits
Speech Verification feature extraction and selection,
Poles and Zeros Correlation Levinson – Durbin Markov (HMW) DTW
pattern matching, classification.
![Page 8: Speech Recognition](https://reader035.fdocuments.us/reader035/viewer/2022081413/547d699db4af9fa2088b45d4/html5/thumbnails/8.jpg)
Speech Recognition
0 100 200 300 400 500 600-40
-20
0
20
40
60
80
100
Correlation
(MATLAB)
0 0.5 1 1.5 2 2.5
x 104
-1
-0.8
-0.6
-0.4
-0.2
0
0.2
0.4
0.6
0.8
1
Signal Acquisition
Original
Pattern
![Page 9: Speech Recognition](https://reader035.fdocuments.us/reader035/viewer/2022081413/547d699db4af9fa2088b45d4/html5/thumbnails/9.jpg)
Speech Recognition
Poles and Zeros
(MATLAB)
0 0.5 1 1.5 2 2.5
x 104
-1
-0.8
-0.6
-0.4
-0.2
0
0.2
0.4
0.6
0.8
1
Signal Acquisition
Original
Pattern
![Page 10: Speech Recognition](https://reader035.fdocuments.us/reader035/viewer/2022081413/547d699db4af9fa2088b45d4/html5/thumbnails/10.jpg)
Application in Control
Elevator
![Page 11: Speech Recognition](https://reader035.fdocuments.us/reader035/viewer/2022081413/547d699db4af9fa2088b45d4/html5/thumbnails/11.jpg)
Application in Control Speech Biometric Recognition
Used to determine the stress status.
Stress Control using a special kind of music.
![Page 12: Speech Recognition](https://reader035.fdocuments.us/reader035/viewer/2022081413/547d699db4af9fa2088b45d4/html5/thumbnails/12.jpg)
Application in Control Control for Robot Automatic translation Automotive speech recognition Court reporting (Realtime Voice Writing) Speech Biometric Recognition Hands- free computing Home automation Pronunciation evaluation in computer-aided language learning
applications
Transcription (digital speech-to-text).
![Page 13: Speech Recognition](https://reader035.fdocuments.us/reader035/viewer/2022081413/547d699db4af9fa2088b45d4/html5/thumbnails/13.jpg)
Conclusions Speech recognition involves the
ability to match a voice pattern against a provided or acquired vocabulary
Speech recognition is used to make control
Speech recognition has an acceptable accuracy, but better accuracy implies less speed.
![Page 14: Speech Recognition](https://reader035.fdocuments.us/reader035/viewer/2022081413/547d699db4af9fa2088b45d4/html5/thumbnails/14.jpg)
ReferencesIEEE SIGNAL PROCESSING MAGAZINEPROCEEDINGS OF THE IEEE
WANG Ye-Yi,Deng Li and Acero Alex, Spoken Language Understanding, IEEE SIGNAL PROCESSING MAGAZINE [16] SEPTEMBER 2005.
CAMPBELL JOSEPH P. Speaker Recognition: A Tutorial, PROCEEDINGS OF THE IEEE, VOL. 85, NO. 9, SEPTEMBER 1997
DENG Li, Wang Kuansan and Chou Wu, Speech Technology and Systems in Human-Machine Communication, IEEE SIGNAL PROCESSING MAGAZINE [12] SEPTEMBER 2005