Summary of Dynamic Humtrans: Humming Transcription Using Cnns and Dynamic Programming, by Shubham Gupta and Isaac Neri Gomez-sarmiento and Faez Amjed Mezdari and Mirco Ravanelli and Cem Subakan
Dynamic HumTrans: Humming Transcription Using CNNs and Dynamic Programming
by Shubham Gupta, Isaac Neri Gomez-Sarmiento, Faez Amjed Mezdari, Mirco Ravanelli, Cem Subakan
First submitted to arxiv on: 7 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Sound (cs.SD); Audio and Speech Processing (eess.AS)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed approach for humming transcription combines a CNN-based architecture with a dynamic programming-based post-processing algorithm, utilizing the HumTrans dataset. The approach identifies and addresses problems with offset and onset ground truth annotations, offering heuristics to improve these annotations. This results in a corrected dataset that will aid future research. The method achieves state-of-the-art (SOTA) transcription accuracy when compared to several others. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Humming transcription is the process of converting humming sounds into written music. Researchers have developed a new way to do this using a combination of computer algorithms and a special dataset called HumTrans. They fixed some problems with the existing annotations in the dataset, which will help future studies. The team’s approach performed better than others at transcribing humming sounds. |
Keywords
» Artificial intelligence » Cnn
