Abstract
We report on some rudimentary experiments involving speech understanding devices which adaptively acquire the language for their task. Such systems have two unique characteristics. First, no text is provided to the device, in contrast to all other existing speech understanding systems. Second, the vocabulary and grammar are unconstrained, being acquired by the device during the course of performing its task. This is also in contrast to all other systems, where the salient vocabulary and grammar are preprogrammed. The experimental mechanism is a connectionist network embedded in a feedback control system.
| Original language | English (US) |
|---|---|
| Title of host publication | Plenary, Special, Audio, Underwater Acoustics, VLSI, Neural Networks |
| Publisher | Publ by IEEE |
| Volume | 1 |
| ISBN (Print) | 0780309464 |
| State | Published - 1993 |
| Externally published | Yes |
| Event | 1993 IEEE International Conference on Acoustics, Speech and Signal Processing - Minneapolis, MN, USA Duration: Apr 27 1993 → Apr 30 1993 |
Other
| Other | 1993 IEEE International Conference on Acoustics, Speech and Signal Processing |
|---|---|
| City | Minneapolis, MN, USA |
| Period | 4/27/93 → 4/30/93 |
ASJC Scopus subject areas
- Software
- Signal Processing
- Electrical and Electronic Engineering