We lifted 2 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| jordipons/EUSIPCO2017 | canonical | 2 of 2 |
| Function | Status | Where it lives |
|---|---|---|
| apply_penalty | Ran | jordipons/EUSIPCO2017/src/lasagne/regularization.py code served (permissive licence) · get_code("f36daf72814d106b") |
| squared_error | Ran | jordipons/EUSIPCO2017/src/lasagne/objectives.py code served (permissive licence) · get_code("5e68226cfc99fbe6") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
The focus of this work is to study how to efficiently tailor Convolutional Neural Networks (CNNs) towards learning timbre representations from log-mel magnitude spectrograms. We first review the trends when designing CNN architectures. Through this literature overview we discuss which are the crucial points to consider for efficiently learning timbre representations using CNNs. From this discussion we propose a design strategy meant to capture the relevant time-frequency contexts for learning timbre, which permits using domain knowledge for designing architectures. In addition, one of our main goals is to design efficient CNN architectures -- what reduces the risk of these models to over-fit, since CNNs' number of parameters is minimized. Several architectures based on the design principles we propose are successfully assessed for different research tasks related to timbre: singing voice phoneme classification, musical instrument recognition and music auto-tagging.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1703.06697")
get_code_for_paper("1703.06697")
have("1703.06697")
Connect an agent — have() is free.