A neuro-fuzzy system for sequence alignment on two levels.

The similarity judgement of two sequences is often decomposed in similarity judgements of the sequence events with an alignment process. However, in some domains like speech or music, sequences have an internal structure which is important for intelligent processing like similarity judgements. In an alignment task, this structure can be reflected more appropriately by using two levels i nstead of aligning event by event. This idea is related to the structural alignment fr amework by Markman and Gentner. Our aim is to align sequences by modelling the segmenting and matching of groups in an input sequence in relation to a target sequence, detecting variations or errors. This is realised as an integrated process, using a neuro-fuzzy system. The selection of segmentations and alignments is based on fuzzy rules which allow the integration of expert knowledge via feature definitions, rule structure, and rule weights. The rule weights can be optimised effectively with an algorithm adapted from neural networks. Thus, the results from the optimisation process are still interpretable. The system has been implemented and tested successfully in a sample application for the recognition of musical rhythm patterns.

[1]  G. A. Miller.  THE PSYCHOLOGICAL REVIEW THE MAGICAL NUMBER SEVEN, PLUS OR MINUS TWO: SOME LIMITS ON OUR CAPACITY FOR PROCESSING INFORMATION 1 , 1956 .

[2]  Diana Deutsch,et al.  Grouping Mechanisms in Music , 1999 .

[3]  Tillman Weyde,et al.  Design and Optimization of Neuro-Fuzzy-Based Recognition of Musical Rhythm Patterns , 2003 .

[4]  Detlef Nauck,et al.  Neuro-Fuzzy Systems: Review And Prospects , 1997 .

[5]  Gerhard Widmer,et al.  The Musical Expression Project: A Challenge for Machine Learning and Knowledge Discovery , 2001, PKDD.

[6]  Jean-Gabriel Ganascia,et al.  Pattern Detection and Discovery: The Case of Music Data Mining , 2002, Pattern Detection and Discovery.

[7]  Olivier Lartillot,et al.  Generalized Musical Pattern Discovery by Analogy from Local Viewpoints , 2002, Discovery Science.

[8]  R. Yager.  On a general class of fuzzy connectives , 1980 .

[9]  Geraint A. Wiggins,et al.  MEMORY AND MELODIC DENSITY: A MODEL FOR MELODY SEGMENTATION , 2003 .

[10]  Cihan H. Dagli.  Smart engineering system design: neural networks, fuzzy logic, evolutionary programming, data mining and complex systems : proceedings of the Artificial Neural Networks in Engineering Conference (ANNIE2001), held November 4-7, 2001, in St. Louis, Missouri, U.S.A. , 1999 .

[11]  Arthur B. Markman,et al.  Structural alignment, similarity, and the internal structure of category representations , 2001, Similarity and Categorization.

[12]  R. Jackendoff,et al.  A Generative Theory of Tonal Music , 1985 .

[13]  Detlef Nauck,et al.  Foundations Of Neuro-Fuzzy Systems , 1997 .

[14]  Dan Gusfield,et al.  Algorithms on Strings, Trees, and Sequences - Computer Science and Computational Biology , 1997 .

[15]  Emilios Cambouropoulos,et al.  The Local Boundary Detection Model (LBDM) and its Application in the Study of Expressive Timing , 2001, ICMC.

[16]  Tillman Weyde,et al.  RECOGNITION OF MUSICAL RHYTHM PATTERNS BASED ON A NEURO-FUZZY-SYSTEM , 2001 .

[17]  Tillman Weyde,et al.  Structure recognition on sequences with a neuro-fuzzy-system , 2003, EUSFLAT Conf..

[18]  Sean R. Eddy,et al.  Biological Sequence Analysis: Probabilistic Models of Proteins and Nucleic Acids , 1998 .

[19]  Q. Summerfield.  Book Review: Auditory Scene Analysis: The Perceptual Organization of Sound , 1992 .

[20]  Ulrike Hahn,et al.  What makes words sound similar? , 2005, Cognition.

[21]  Tillman Weyde.  Lern- und wissensbasierte Analyse von Rhythmen , 2003 .

[22]  W. Heeringa,et al.  Computational Comparison and Classification of Dialects , 2001 .

[23]  Tillman Weyde,et al.  Integrating Segmentation and Similarity in Melodic Analysis , 2002 .

[24]  Grzegorz Kondrak,et al.  Phonetic Alignment and Similarity , 2003, Comput. Humanit..

[25]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[26]  Paul Fraisse,et al.  TIME AND RHYTHM PERCEPTION , 1978 .