Name
Title | ||
|---|---|---|
Automatic Speech Recognition Based on Ultrasonic Doppler Sensing for European Portuguese. |
Abstract | ||
|---|---|---|
Conventional Automatic Speech Recognition systems solely rely on acoustic information, making them susceptible to problems, like environmental noise, privacy, information disclosure and also excluding users with speech impairments. An Ultrasonic Doppler Sensing (UDS) based interface may be used to tackle these issues since it does not rely on audio signal information. This paper describes the first speech recognition experiments based on UDS for European Portuguese (EP). The work here presented analyzes the UDS signal and explores the recognition of EP digits and minimal pairs of words that only differ on nasality of one of the phones. The results of our experiments show a best word error rate of 27.8% using data collected with the device at different distances from the speaker in an isolated word recognition problem. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1007/978-3-642-35292-8_24 | ADVANCES IN SPEECH AND LANGUAGE TECHNOLOGIES FOR IBERIAN LANGUAGES |
Keywords | Field | DocType |
Ultrasonic Doppler Sensing,Silent Speech,European Portuguese,Nasality | European Portuguese,Nasality,Audio signal,Ultrasonic sensor,Computer science,Word error rate,Word recognition,Speech recognition,Doppler effect,Environmental noise | Conference |
Volume | ISSN | Citations |
328 | 1865-0929 | 2 |
PageRank | References | Authors |
0.41 | 6 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| João Freitas | 1 | 17 | 5.40 |
| António J. S. Teixeira | 2 | 152 | 35.26 |
| Francisco A. C. Vaz | 3 | 19 | 3.18 |
| Miguel Sales Dias | 4 | 133 | 24.96 |