HMM-based musical query retrieval

Shifrin, Jonah; Pardo, Bryan; Meek, Colin; Birmingham, William P.

doi:10.1145/544220.544291

Cited by 37 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Together, we have been exploring the design of QBH systems Hu and Dannenberg 2002;Meek and Birmingham 2002a;Pardo and Birmingham 2002;Shifrin et al 2002). We have developed a variety of algorithms based on hidden Markov models and contour matching.…”

Section: The Musart Projectmentioning

confidence: 99%

The MUSART Testbed for Query-by-Humming Evaluation

Dannenberg

Birmingham

Tzanetakis

et al. 2004

Computer Music Journal

Self Cite

View full text Add to dashboard Cite

Section: The Musart Projectmentioning

confidence: 99%

The MUSART Testbed for Query-by-Humming Evaluation

Dannenberg

Birmingham

Tzanetakis

et al. 2004

Computer Music Journal

Self Cite

View full text Add to dashboard Cite

“…Several probabilistic methods (HMM-based) have been developed for speech recognition and music retrieval [14,31,34,36,39,48]. In [31], an extended HMM is used where the target and query notes are associated through a series of hidden states, modeling the local and cumulative error in pitch and durations.…”

Section: Model-based Matchingmentioning

confidence: 99%

A survey of query-by-humming similarity methods

Kotsifakos

Papapetrou

Hollmén

et al. 2012

Proceedings of the 5th International Conference on PErvasive Technologies Related to Assistive Environments

View full text Add to dashboard Cite

Performing similarity search in large databases is a problem of particular interest in many communities, such as music, database, and data mining. Although several solutions have been proposed in the literature that perform well in many application domains, there is no best method to solve this kind of problem in a QueryBy-Humming (QBH) application. In QBH the goal is to find the song(s) most similar to a hummed query in an efficient manner. In this paper, we focus on providing a brief overview of the representations to encode music pieces, and also on the methods that have been proposed for QBH or other similarly defined problems.

show abstract

“…The prior one attracts considerable research efforts because users naturally sing a music piece in notes, and notes are also the fundamental building blocks of MIDI files. Signatures can be extracted as strings [13], n-grams [16][17] [18] or hidden Markov chains [19] [20], and similarity between user query and database files can be calculated by approximate string matching algorithms [14] [15] or in a probabilistic manner. Most systems of this category depend on accurate note segmentation [21] from the pitch sequence of a user query, which is sensitive to noises and therefore limits the system's retrieval accuracy.…”

Section: Introductionmentioning

confidence: 99%

An FPGA based parallel architecture for music melody matching

Wang

Liu

2013

Proceedings of the ACM/SIGDA International Symposium on Field Programmable Gate Arrays

View full text Add to dashboard Cite

We propose an FPGA-based high performance parallel architecture for music retrieval through singing. The database consists of monophonic MIDI files which are modeled into strings, and the user sung query is modeled as a set of regular expressions (regexp), with consideration of possible key transpositions and tempo variations to tolerate imperfectly sung queries. An approximate regexp matching algorithm is developed to calculate the similarity between a regexp and a string, using edit distance as the metrics. The algorithm supports user sung queries starting anywhere in the database song, not necessarily from the beginning. Using the proposed formal models and algorithms, the similarity between the user sung query and each song in the database can be evaluated and the top-10 most similar results will be reported.We designed the approximate regexp matching algorithm in such way that all terms of the regexp can execute concurrently, which perfectly fits the massive parallelism provided by FPGA. The FPGA implemented melody matching engine (MME) is a parameterized modular architecture that can be reconfigured to implement different regexps by simply updating their parameter registers, and can therefore avoid the time-consuming code re-synthesis. MME also includes an on-board DDR2 memory to store the database, so that they can be read in to calculate edit distances locally on the board. This way, each MME forms a self-contained system and multiple MMEs can be clustered to increase parallel processing power, with virtually no overhead. MME is evaluated using the query corpus of ThinkIT with 355 sung files and database of 5563 MIDI files. It achieves a top-10 hit rate of 90.7% and a runtime of 19.4 seconds, averaging 54.6 milliseconds for a single query. MME achieves significant speedup over software-based systems while providing the same level of flexibility.

show abstract

HMM-based musical query retrieval

Cited by 37 publications

References 5 publications

The MUSART Testbed for Query-by-Humming Evaluation

The MUSART Testbed for Query-by-Humming Evaluation

A survey of query-by-humming similarity methods

An FPGA based parallel architecture for music melody matching

Contact Info

Product

Resources

About