A Conditional Model for Tonal Analysis

Radicioni, Daniele Paolo; Esposito, Roberto

doi:10.1007/11875604_72

Cited by 3 publications

(18 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Within the music analysis area, we present an application for tonal harmony music analysis [24]. Here tonal harmony analysis is understood as segmenting and labeling an audio signal according to its underlying harmony [25].…”

Section: Goal Of the Papermentioning

confidence: 99%

“…Let c i , i ∈ [1,24] denote the 24 chords of the chord lexicon. We observe a succession of x n = o n , n ∈ [0, N − 1] 12dimensional chroma vectors, n being the time index, and N being the total number of beat-synchronous frames of the analyzed song.…”

Section: B Hmms Vs Crfs For Tonal Harmony 1) Baseline Hmm For Chordmentioning

confidence: 99%

“…The chord progression is modeled as an ergodic 24-state HMM with a hidden variable and a single observable variable at each time step. Each hidden state y n , n ∈ [0, N − 1] is a chord c i , i ∈ [1,24] of the lexicon and is observed through a chroma observation, with emission probability p obs HMM (x n y n ). A state-transition matrix based on musical knowledge that reflects chord transition rules is used to model the transition probabilities p trans HMM (y n y n−1 ) 16 .…”

Section: B Hmms Vs Crfs For Tonal Harmony 1) Baseline Hmm For Chordmentioning

confidence: 99%

“…Some chords are heard as more stable within an established tonal context [98]. Various key templates, which represent the importance of each of the 24 triads within a given key have been proposed in the literature, as the set of 24 24-dimensional WMCR key templates T l key , l ∈ [1,24] proposed in [28]. Such prior information about keys and chords relationship can be incorporated in the CRF through additional observation features.…”

Section: ) Enriched Crf For Chord Estimation (Crfpriorkey)mentioning

confidence: 99%

See 3 more Smart Citations

Models for Music Analysis From a Markov Logic Networks Perspective

Papadopoulos¹,

Tzanetakis²

2017

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Analyzing and formalizing the intricate mechanisms of music is a very challenging goal for Artificial Intelligence. Dealing with real audio recordings requires the ability to handle both uncertainty and complex relational structure at multiple levels of representation. Until now, these two aspects have been generally treated separately, probability being the standard way to represent uncertainty in knowledge, while logical representation being the standard way to represent knowledge and complex relational information. Several approaches attempting a unification of logic and probability have recently been proposed. In particular Markov Logic Networks (MLNs) which combine first-order logic and probabilistic graphical models have attracted increasing attention in recent years in many domains. This paper introduces MLNs as a highly flexible and expressive formalism for the analysis of music that encompasses most of the commonly used probabilistic and logic-based models. We first review and discuss existing approaches for music analysis. We then introduce MLNs in the context of music signal processing by providing a deep understanding of how they specifically relate to traditional models, specifically Hidden Markov Models and Conditional Random Fields. We then present a detailed application of MLNs for tonal harmony music analysis that illustrates the potential of this framework for music processing.

show abstract

Section: Goal Of the Papermentioning

confidence: 99%

Section: B Hmms Vs Crfs For Tonal Harmony 1) Baseline Hmm For Chordmentioning

confidence: 99%

Section: B Hmms Vs Crfs For Tonal Harmony 1) Baseline Hmm For Chordmentioning

confidence: 99%

Section: ) Enriched Crf For Chord Estimation (Crfpriorkey)mentioning

confidence: 99%

See 2 more Smart Citations

Models for Music Analysis From a Markov Logic Networks Perspective

Papadopoulos¹,

Tzanetakis²

2017

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

show abstract

“…We have designed a system for tonal analysis, breve, where the analysis task is cast to a supervised sequential learning (SSL) problem [7]. From a methodological viewpoint, it transports to the musical domain the state-ofart machine learning conditioned models paradigm, originally devised for the part-of-speech (POS) tagging problem [8].…”

Section: Introductionmentioning

confidence: 99%

Tonal Harmony Analysis: A Supervised Sequential Learning Approach

Radicioni

Esposito

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

We have recently presented CarpeDiem, an algorithm that can be used for speeding up the evaluation of Supervised Sequential Learning (SSL) classifiers. CarpeDiem provides impressive time performance gain over the state-of-art Viterbi algorithm when applied to the tonal harmony analysis task. Along with interesting computational features, the algorithm reveals some properties that are of some interest to Cognitive Science and Computer Music. To explore the question whether and to what extent the implemented system is suitable for cognitive modeling, we first elaborate about its design principles, and then assess the quality of the analyses produced. A threefold experimentation reviews the learned weights, the classification errors, and the search space in comparison to the actual problem space; data about these points are reported and discussed.AI in Art and Music; Cognitive Modeling; Machine learning; Music Analysis.

show abstract

CarpeDiem

Esposito¹,

Radicioni²

2007

Proceedings of the 24th International Conference on Machine Learning

Self Cite

View full text Add to dashboard Cite

In this paper we present a novel algorithm, CarpeDiem. It significantly improves on the time complexity of Viterbi algorithm, preserving the optimality of the result. This fact has consequences on Machine Learning systems that use Viterbi algorithm during learning or classification. We show how the algorithm applies to the Supervised Sequential Learning task and, in particular, to the HMPerceptron algorithm. We illustrate CarpeDiem in full details, and provide experimental results that support the proposed approach.

show abstract

A Conditional Model for Tonal Analysis

Cited by 3 publications

References 11 publications

Models for Music Analysis From a Markov Logic Networks Perspective

Models for Music Analysis From a Markov Logic Networks Perspective

Tonal Harmony Analysis: A Supervised Sequential Learning Approach

CarpeDiem

Contact Info

Product

Resources

About