A Local Maximum Phrase Detection Method for Analyzing Phrasing Strategies in Expressive Performances
نویسندگان
چکیده
This paper proposes a Local Maximum Phrase Detection (LMPD) method for the analysis of phrasing strategies in expressive performances. The LMPD method systematically extracts a quantitative representation of phrasing strategy by equating the occurrence of a local maximum in the loudness curve with the occurrence of a phrase or sub-phrase. We further define mathematical descriptors for phrase strength and volatility, and phrase typicality, for comparing phrasing strategies among performances. Phrase strength measures the prominence or clarity of a phrase, and the volatility is defined as the standard deviation of the phrase strengths within a performance. Phrase typicality quantifies the degree to which a phrase peak location is characteristic among the performances polled. We illustrate the LMPD method using preliminary results from its application to eleven commercially available audio recordings of a solo violin Bach Sonata.
منابع مشابه
A Dynamic Programming Approach to the Extraction of Phrase Boundaries from Tempo Variations in Expressive Performances
We present an approach to phrase segmentation that starts with an expressive music performance. Previous research has shown that phrases are delineated by tempo speedups and slowdowns. We propose a dynamic programming algorithm for extracting phrases from tempo information. We test two hypotheses for modeling phrase tempo shapes: a quadratic model, and a spline curve. We test the two models on ...
متن کاملPlaying Mozart by Analogy: Learning Multi-level Timing and Dynamics Strategies
The paper describes basic research in the area of machine learning and musical expression. A first step towards automatic induction of multi-level models of expressive performance (currently only tempo and dynamics) from real performances by skilled pianists is presented. The goal is to learn to apply sensible tempo and dynamics ‘shapes’ at various levels of the hierarchical musical phrase stru...
متن کاملPaper Review: Playing Mozart by Analogy: Learning Multi-level Timing and Dynamics Strategies
Gerhard Widmer and Asmir Tobudic discuss a method of machine learning involving the various hierarchical levels at which musicians operate in their paper entitled, " Playing Mozart by Analogy: Learning Multi-level Timing and Dynamics Strategies ". In the introduction of the paper, their goal is stated outright: to investigate to what extent a machine can automatically build, via inductive learn...
متن کاملLength Optimized Chinese Prosodic Phrasing Model
The phrase length information is an important cue for assigning prosodic phrase breaks. However, it has not been fully utilized in the present TTS systems. Based on the study of the phrase length distribution and the interaction between prosodic words and prosodic phrases, this paper proposes a new stochastic model named phrase-length model for using the phrase length information. And it is pro...
متن کاملRecognizing phrase and utterance as prosodic units in non-tonal dialects of Kammu
This paper presents a study of prosodic phrasing in a non-tonal dialect of Kammu, a MonKhmer language spoken in Northern Laos. Prosodic phrasing is seen as correlated with syntactic and informational structures, and the description is made referring to these two levels. The material investigated comprises sentences of different lengths and syntactic structures, uttered by seven male speakers. I...
متن کامل