When Counterpoint Meets Chinese Folk Melodies
Authors: Nan Jiang, Sheng Jin, Zhiyao Duan, Changshui Zhang
NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments show that the proposed algorithm achieves better subjective and objective results than the baselines. |
| Researcher Affiliation | Academia | Institute for Artificial Intelligence, Tsinghua University (THUAI), State Key Lab of Intelligent Technologies and Systems, Beijing National Research Center for Information Science and Technology (BNRist), Department of Automation, Tsinghua University, Beijing, China Department of Electrical and Computer Engineering, University of Rochester jiangn15@mails.tsinghua.edu.cn js17@mails.tsinghua.edu.cn zhiyao.duan@rochester.edu zcs@mail.tsinghua.edu.cn |
| Pseudocode | No | The paper describes the proposed system and its components (Generator, Style Rewarder, Inter-Rewarder) but does not provide any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper mentions supplementary material multiple times for additional details and examples, but it does not contain an explicit statement about releasing source code or provide a link to a code repository for the methodology described. |
| Open Datasets | Yes | Two datasets are used in our work. The first one consists of Chinese folk melodies from the Essen Folksong Collection1. They are performance-feature-removed transcriptions, comprising 2250 traditional Chinese folk songs, from Han, Natmin, Shanxi, and Xinhua areas. ... 1https://kern.humdrum.org/cgi-bin/browse?l=/essen The other dataset is the Bach Chorale Dataset in music21. |
| Dataset Splits | Yes | We randomly split them into 80% train, 10% validation, and 10% test. |
| Hardware Specification | No | The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory) used for running its experiments, only describing the computational processes. |
| Software Dependencies | No | The paper mentions 'music21 [10]' in the context of filtering dataset pieces, but it does not provide specific version numbers for `music21` or any other software libraries or dependencies used in their implementation. |
| Experiment Setup | No | The paper states that 'More information about the training process and hyper-parameters of Folk Duet and the baselines is contained in the supplementary material,' indicating that these specific details are not present in the main text. |