Topological fingerprints for audio identification
We present a topological audio fingerprinting approach for robustly identifying dupli5 cate audio tracks. Our method applies persistent homology on local spectral decompositions of audio signals, using filtered cubical complexes computed from mel-spectrograms. By encoding the audio content in terms...
| Main Authors: | , , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
Society for Industrial and Applied Mathematics
2024
|