Difference between revisions of "ISSS608 2017-18 T3 Kiriti Yelamanchali Q2"
Jump to navigation
Jump to search
Kiritiy.2017 (talk | contribs) |
Kiritiy.2017 (talk | contribs) |
||
| Line 51: | Line 51: | ||
3. The wavelet spectographs of one bird are observed across different qualities, to have a visual representation of the quality | 3. The wavelet spectographs of one bird are observed across different qualities, to have a visual representation of the quality | ||
| − | [[File:Kiriti pipit comaprisions.png]|600 px] | + | [[File:Kiriti pipit comaprisions.png]|600 px]] |
It is evident that, the Qualities marked as A and B are useful in terms of model training. | It is evident that, the Qualities marked as A and B are useful in terms of model training. | ||
Revision as of 23:23, 8 July 2018
VAST CHALLENGE 2018: MC1
|
|
|
|
|
|
|
|
Deep Learning Model to recognize bird calls
For this analysis, a deep learning model is built to recognize the bird calls.
- Python library librosa is ised for this purpose
1. The cleaned csv from data preparation stage is loaded into the pandas dataframe.
2. A new dataframe column is created to match the mp3 file names in the data, after a bit of cleaning.
3. The wavelet spectographs of one bird are observed across different qualities, to have a visual representation of the quality [[File:Kiriti pipit comaprisions.png]|600 px]]
It is evident that, the Qualities marked as A and B are useful in terms of model training.
