\sigma GTTM III: Learning-Based Time-Span Tree Generator Based on PCFG
نویسندگان
چکیده
We propose an automatic analyzer for acquiring a time-span tree based on the generative theory of tonal music (GTTM). Although analyzer based on GTTM was previously proposed, it requires manually tweaking the 46 adjustable parameters on a computer screen in order to analyze them properly. We reformalized the time-span reduction in GTTM based on a statistical model called probabilistic context-free grammar, which enables us to acquire the most probabilistic time-span tree. We applied leave-one-out cross validation using three hundred sets training data, which revealed that our analyzer outperformed the previous one.
منابع مشابه
ATTA: Automatic Time-Span Tree Analyzer Based on Extended GTTM
This paper describes a music analyzing system called the automatic time-span tree analyzer (ATTA), which we have developed. The ATTA derives a time-span tree that assigns a hierarchy of 'structural importance' to the notes of a piece of music based on the generative theory of tonal music (GTTM). Although the time-span tree has been applied with music summarization and collaborative music creati...
متن کاملdeepGTTM-I: Local Boundaries Analyzer based on A Deep Learning Technique
Abstract. This paper describes a method that enables us to detect the local boundaries of a generative theory of tonal music (GTTM). Although systems that enable us to automatically acquire local boundaries have been proposed such as a full automatic time-span tree analyzer (FATTA) or σGTTM, musicologists have to correct the boundaries because of numerous errors. In light of this, we propose a ...
متن کاملAutomatic Melodic Reduction Using a Supervised Probabilistic Context-Free Grammar
This research explores a Natural Language Processing technique utilized for the automatic reduction of melodies: the Probabilistic Context-Free Grammar (PCFG). Automatic melodic reduction was previously explored by means of a probabilistic grammar [11] [1]. However, each of these methods used unsupervised learning to estimate the probabilities for the grammar rules, and thus a corpusbased evalu...
متن کاملFatta: Full Automatic Time-Span Tree Analyzer
We developed a music analysis system called a full automatic time-span tree analyzer (FATTA), which analyzes a piece of music based on the generative theory of tonal music (GTTM). We previously developed an automatic time-span tree analyzer (ATTA), which can acquire a time-span tree of GTTM. Although the ATTA has adjustable parameters for controlling the weight or the priority of each rule, the...
متن کاملDeepGTTM-II: Automatic Generation of Metrical Structure based on Deep Learning Technique
This paper describes an analyzer that automatically generates the metrical structure of a generative theory of tonal music (GTTM). Although a fully automatic time-span tree analyzer has been developed, musicologists have to correct the errors in the metrical structure. In light of this, we use a deep learning technique for generating the metrical structure of a GTTM. Because we only have 300 pi...
متن کامل