About

Log in?

DTU users get better search results including licensed content and discounts on order fees.

Anyone can log in and get personalized features such as favorites, tags and feeds.

Log in as DTU user Log in as non-DTU user No thanks

DTU Findit

Recent

Boolean: (bicycle AND helmet) OR (head AND protection) (always group AND in parenthesis)
Title: title:(climate change)
Author: author:("bohr niels" OR "bohr n") (avoid only full first name)
Phrase: "water pump control" (does not work with wildcards)
Wildcards: wom?n pharm*

More help on how to search

Flexible matching

About search syntax

Search syntax Advanced
Close advanced
{{problem}}
By field Using AND/OR By author
This tool can help you build boolean queries suitable for doing a broad search for different synonyms or spellings of each word. Start via the drop-down below or just start typing in the search field.
{{ row.typeTitle }}: ( )

Since our index often lack the full first name of people it can be difficult to correctly search by author.

Fill in the fields and let us help you build a good query:

If you need to find everything possible, consider only searching by last name.

Use "Starting year" to ignore publications out of year range.

Author: Hansen remove
Filter results...

Interpreted as:

title:(Learning AND and AND clean-up AND in AND a AND large AND scale AND music AND database)

Suggestions: Include records that partially match the query

Filter results
Access
Type
Language
Year
From DTU
Advanced
Previous 1 - 2 of 2 Next
Export
10 items by relevance
1 Conference paper

Learning and clean-up in a large scale music database

Hansen, L. K.; Lehn-Schioler, T.; Petersen, K. B.; Arenas-Garcia, J.; Larsen, J.; Jensen, S. H.

2007 15th European Signal Processing Conference — 2007, pp. 946-950

We have collected a database of musical features from radio broadcasts and CD collections (N > 105). The database poses a number of hard modelling challenges including: Segmentation problems and missing and wrong meta-data. We describe our efforts towards cleaning the data using probability density estimation. We train conditional densities for checking the relation between meta-data and music features, and un-conditional densities for spotting unlikely music features. We show that the rejected samples indeed represent various types of problems in the music data. The models ma...

Year: 2007

Language: English

More...
ogb ecaki dp fmhjln
2 Conference paper

Learning and clean-up in a large scale music database

Hansen, Lars Kai; Lehn-Schiøler, Tue; Petersen, Kaare Brandt; Arenas-Garcia, Jeronimo; Larsen, Jan; Jensen, Søren Holdt

Eusipco 2007 — 2007

We have collected a database of musical features from radio broadcasts (N > 100.000). The database poses a number of hard modeling challenges including: Segmentation problems and missing metadata. We describe our efforts towards cleaning the database using signal processing and machine learning

Year: 2007

Language: English

More...
jbelnc ia gdho fkpm

DTU users get better search results including licensed content and discounts on order fees.

Log in as DTU user