Advancing Electromyographic Continuous Speech Recognition: Signal Preprocessing and Modeling
Speech is the natural medium of human communication, but audible speech can be overheard by bystanders and excludes speech-disabled people. This work presents a speech recognizer based on surface electromyography, where electric potentials of the facial muscles are captured by surface electrodes, al...
| Other Authors: | |
|---|---|
| Format: | eBook |
| Language: | Inglés |
| Published: |
KIT Scientific Publishing
2014
|
| Subjects: | |
| See on Biblioteca Universitat Ramon Llull: | https://discovery.url.edu/permalink/34CSUC_URL/1im36ta/alma991009437721406719 |
| Summary: | Speech is the natural medium of human communication, but audible speech can be overheard by bystanders and excludes speech-disabled people. This work presents a speech recognizer based on surface electromyography, where electric potentials of the facial muscles are captured by surface electrodes, allowing speech to be processed nonacoustically. A system which was state-of-the-art at the beginning of this book is substantially improved in terms of accuracy, flexibility, and robustness. |
|---|---|
| Physical Description: | 1 electronic resource (XVIII, 226 p. p.) |
| Access: | Open access |
