|
| EPSRC Reference: |
GR/M84497/01 |
| Title: |
ROPA: AUTOMATIC RECOGNITION OF MUSICAL INSTRUMENTS USING HIDDEN MARKOV MODELS |
| Principal Investigator: |
Professor N Canagarajah |
| Other Investigators: |
|
| Researcher Co-investigator: |
|
| Project Partner: |
|
| Department: |
Electrical and Electronic Engineering |
| Organisation: |
University of Bristol |
| Scheme: |
ROPA |
| Starts: |
01 February 2000 |
Ends: |
31 January 2002 |
Value (£): |
100,431
|
| EPSRC Research Topic Classifications: |
| User Interface Technologies |
|
|
| EPSRC Industrial Sector Classifications: |
| No relevance to Underpinning Sectors |
|
|
| Related Grants: |
|
| Panel History: |
|
|
Summary |
|
One of the goals of computational auditory scene analysis is to create systems that can learn to recognise/separate sound sources. The purr of this research project is to develop a system for automatic recognition of musical instruments based on time-frequency representations and statistical modelling techniques. In particular we will investigate whether Hidden Markov Models could be used to aid recognition based c musical phrases. This modelling approach to recognition based on sequential attributes of music is quite unique and significantly differen from the current approaches, where instantaneous sounds properties are employed on an individual frame basis. If successful this could provide a novel platform for music analysis which will be useful in a number of applications including music transcription, signal separati for hearing aids and multimedia indexing.
|
| Final Report Summary |
|
No Abstract found on this grant
|
| Further Information: |
|
| Organisation Website: |
http://www.bris.ac.uk |
|
|