Melody Harmonization With Interpolated Probabilistic Models
Bibliographic Data
| ID | 5304992 |
|---|---|
| Authors | Stanislaw Raczynski (0000-0003-1501-4205, Gdańsk University of Technology, corresponding author), Stanisław A Raczyński, Satoru Fukayama (0000-0001-6506-2796, The University of Tokyo), Emmanuel Vincent (0000-0002-0183-7289, Institut national de recherche en sciences et technologies du numérique) |
| Year | 2013 |
| Volume | 42 |
| Issue | 3 |
| Pages | 223-235 |
| Publication date | 2013-09-01 |
| Open Access | No |
| Type | ARTICLE |
| Venue | Journal of New Music Research (JOURNAL) |
| Journal identifiers | ISSN: 0929-8215 • E-ISSN: 1744-5027 |
| Publisher | Informa UK Limited (PUBLISHER • GB) |
| DOI | 10.1080/09298215.2013.822000 |
| OpenAlex | W2112221503 |
| Language | EN |
| Citations received | 3 |
| References cited | 15 |
Most melody harmonization systems use the generative hidden Markov model (HMM), which model the relation between the hidden chords and the observed melody. Relations to other variables, such as the tonality or the metric structure, are handled by training multiple HMMs or are ignored. In this paper, we propose a discriminative means of combining multiple probabilistic models of various musical variables by means of model interpolation. We evaluate our models in terms of their cross-entropy and their performance in harmonization experiments. The proposed model offered higher chord root accuracy than the reference musicological rule-based harmonizer by up to 5% absolute
Conditional entropy · Discriminative model · Generative grammar · Generative model · Harmonization · Hidden Markov model · Melody · Musical · Principle of maximum entropy · Probabilistic logic · Speech recognition · Statistical model · Tonality · Computer Science · Music and Audio Processing · Music Technology and Sound Studies · Speech Recognition and Synthesis · Artificial Intelligence
| Citations per year | 0.3 |
|---|---|
| Citation span | 2016 - 2021 (6) |
| Highly cited | No |