Teaching a Music Search Engine Through Play

نویسندگان

  • Bryan Pardo
  • David A. Shamma
چکیده

Systems able to find a song based on a sung, hummed, or whistled melody are called Query-By-Humming (QBH) systems. We propose an approach to improve search performance of a QBH system based on data collected from an online social music game, Karaoke Callout. Users of Karaoke Callout generate training data for the search engine, allowing both ongoing personalization of query processing as well as vetting of database keys. Personalization of search engine user models takes place through using sung examples generated in the course of play to optimize parameters of user models.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Crowdsourcing a Real-world On-line Query by Humming System

Systems able to find a song based on a sung, hummed, or whistled melody are called Query-By-Humming (QBH) systems. Tunebot is an online QBH web service and iPhone app that connects users to the desired recording on Amazon.com or iTunes. Tunebot’s searchable database is composed of thousands of usercontributed melodies. Melodies are collected from user queries, sung contributions and through con...

متن کامل

An Industrial Strength Audio Search Algorithm

We have developed and commercially deployed a flexible audio search engine. The algorithm is noise and distortion resistant, computationally efficient, and massively scalable, capable of quickly identifying a short segment of music captured through a cellphone microphone in the presence of foreground voices and other dominant noise, and through voice codec compression, out of a database of over...

متن کامل

CS229 Project: Music Search Engine

With the abundance of digital music files on the internet, how to efficiently and effectively find a music piece is crucial. Conventional music search systems utilize text information of the music, such as the title of a song, a singer’s name, or the lyrics of a song. In many cases, such text-based music search tool is not sufficient. Often, a user may remember how to sing part of a song he/she...

متن کامل

DOing REusable MUSical Data (DOREMUS)

The aim of this tutorial is first to provide in-depth explanations of DOREMUS, a model for describing music metadata. We will demonstrate how real data coming frommusical libraries can be converted to this model by presenting the whole DOREMUS tools chain. We will illustrate how the DOREMUS data can be used for query answering and consumed through various applications including an exploratory s...

متن کامل

Muma: a Music Search Engine Based on Content Analysis

Existing music search engines are often limited to the textual modality (i.e., searching the textual metadata that are attached to music documents). We introduce here MUMA (http://muma.labs.exalead.com), a new search engine that relies both on textual metadata and signal processing metadata. MUMA allows the user to search for particular chords sequences, for specific moods, and to listen to aut...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2007