An Improved Query by Singing/Humming System Using Melody and Lyrics Information
نویسندگان
چکیده
This paper proposes an improved query by singing/humming (QBSH) system using both melody and lyrics information for achieving better performance. Singing/humming discrimination (SHD) is first performed to distinguish singing from humming queries. For a humming query, we apply a pitch-only melody recognition method that has been used for QBSH task at MIREX with rank-1 performance. For a singing query, we combine the scores from melody recognition and lyrics recognition to take advantage of the extra lyrics information. Lyrics recognition is based on a modified tree lexicon that is commonly used in speech recognition. The performance of the overall QBSH system achieves 39.01% and 23.53% error reduction rates, respectively, for top-20 recognition under two experimental settings, indicating the feasibility of the proposed method.
منابع مشابه
A Lyrics-matching Qbh System for Inter- Active Environments
Query-by-Humming (QBH) is an increasingly prominent technology that allows users to browse through a song database by singing/humming a part of the song they wish to retrieve. Besides these cases, QBH can also be used to track the performance of a user in applications such as Score Alignment and Real-Time Accompaniment. In this paper we present an online QBH algorithm for audio recordings of si...
متن کاملQBH System Using Melody Matching Model based on a String Pattern Matching mechanism of Frequency Contours
Query by humming (QBH) refers to music information retrieval systems where short audio clips of singing or humming act as queries. Melody is considered as the most important feature in the queries and the songs. This system proposes a QBH system Using Melody Matching Model Based on a string pattern matching mechanism of frequency contours, which is used to align the input pitch frequency contou...
متن کاملMelody Retrieval On The Web
The emergence of digital music on the Internet requires new information retrieval methods adapted to specific characteristics and needs. While music retrieval based on the text information, such as title, composers, or subject classification, has been implemented in many existing systems, retrieval of a piece of music based on musical content, especially an incomplete, imperfect recall of a fra...
متن کاملReal-time Accompaniment Using Lyrics-Matching QBH
Query-by-Humming (QBH) is an increasingly popular technology that allows users to browse through a song database by singing/humming a part of the song they wish to retrieve. Besides these cases, QBH can be also used in applications such as Score Alignment and Real-Time Accompaniment, to locate the exact position of the soloist within the piece. We propose a system that initially pinpoints a sin...
متن کاملTwo Note Based Approaches to Query by Singing/Humming
This paper describes the submissions to the MIREX 2006 Query by Singing/Humming task delivered by Fraunhofer IDMT. The approach presented here is based on extracting the pitch out of monophonic singing (or humming), and hereafter segmenting and quantising it into a melody composed of discrete notes. Finally this melody is compared to a database of indexed melodies, using an error tolerant simil...
متن کامل