Abstract
Some existing blind bandwidth extension algorithms are restricted to linear extrapolation, such as linear spectrum replication. In this paper, we propose an improved blind bandwidth extension method using a non-linear extrapolation to reconstruct the missing high-frequency components. By training weights of the neural network in real time, the highband signal can be reconstructed dynamically. Objective and subjective listening tests are used to evaluate the performance of the proposed algorithm, and the results show that it obtains higher quality signals.
| Original language | English |
|---|---|
| Title of host publication | 2010 WRI International Conference on Communications and Mobile Computing, CMC 2010 |
| Pages | 356-360 |
| Number of pages | 5 |
| DOIs | |
| Publication status | Published - 2010 |
| Event | 2010 International Conference on Communications and Mobile Computing, CMC 2010 - Shenzhen, China Duration: 12 Apr 2010 → 14 Apr 2010 |
Publication series
| Name | 2010 WRI International Conference on Communications and Mobile Computing, CMC 2010 |
|---|---|
| Volume | 1 |
Conference
| Conference | 2010 International Conference on Communications and Mobile Computing, CMC 2010 |
|---|---|
| Country/Territory | China |
| City | Shenzhen |
| Period | 12/04/10 → 14/04/10 |
Keywords
- BP algorithm
- Blind bandwidth extension
- Neural network
- Predictive extrapolation
Fingerprint
Dive into the research topics of 'An improved blind bandwidth extension method for audio coding'. Together they form a unique fingerprint.Cite this
Liu, H., Zhao, S., Wang, J., & Kuang, J. (2010). An improved blind bandwidth extension method for audio coding. In 2010 WRI International Conference on Communications and Mobile Computing, CMC 2010 (pp. 356-360). Article 5471455 (2010 WRI International Conference on Communications and Mobile Computing, CMC 2010; Vol. 1). https://doi.org/10.1109/CMC.2010.343