公开(公告)号：KR1020080082022A

公开(公告)日：2008-09-11

申请号：KR1020070011725

申请日：2007-02-05

Applicant: 한국전자통신연구원 ,  한국정보통신대학교 산학협력단

Inventor： 윤정현 ,  김휘용 ,  이희경 ,  이한규 ,  홍진우 ,  김상호 ,  김회린 ,  김성탁

IPC: G06F17/30

CPC classification number: G06F17/30761 ,  G06F17/30749

Abstract: A device and a method for measuring similarity based on feature of music, and a music recommendation system and method using the same are provided to calculate the similarity in an Internet or digital broadcasting environment based on the feature of the preferred music of a user and recommend the music effectively to the user based on the similarity. A music feature extractor(131) extracts feature information, which is at least one of rhythm or tone feature information, reflecting characteristics of music. A music feature information database(132) stores the extracted feature information in a feature vector row. A similarity calculator(133) calculates similarity between music by comparing a music list(16) extracted based on genre/singer information of the current queried music(14) of a user with the feature information of the current queried music or accumulative feature information of the past queried music. An updater updates the feature information of the current queried music to the accumulative feature information of the past queried music. A music recommender generates and provides a recommendation list in high similarity order depending on a similarity calculation result.

Abstract translation: 提供了一种基于音乐特征来测量相似度的装置和方法，并且提供了使用该装置和音乐推荐系统和方法的方法，以基于用户的首选音乐的特征来计算因特网或数字广播环境中的相似度，并推荐 基于相似性，音乐有效地向用户提供。 音乐特征提取器（131）提取特征信息，其是节奏或音调特征信息中的至少一个，其反映音乐的特征。 音乐特征信息数据库（132）将所提取的特征信息存储在特征向量行中。 相似度计算器（133）通过将根据用户的当前查询音乐（14）的类型/歌手信息提取的音乐列表（16）与当前查询音乐的特征信息或累积特征信息 过去的查询音乐。 更新者将当前查询的音乐的特征信息更新为过去查询的音乐的累积特征信息。 音乐推荐器根据相似度计算结果产生并以高相似性顺序提供推荐列表。

公开(公告)号：KR100774708B1

公开(公告)日：2007-11-08

申请号：KR1020060066766

申请日：2006-07-18

Applicant: 한국정보통신대학교 산학협력단

Inventor： 김회린 ,  박만수 ,  김성탁 ,  김상호

IPC: H04B1/40 ,  G11B20/10

CPC classification number: G06F17/30743 ,  H04M3/42017

Abstract: A bell sound and/or RBT(Ring Back Tone) generation system of a user preference melody section through real-time music recognition and a method are provided to detect a sound source and an offset position through music recognition if a user inputs a particular melody section of the preferred sound source as an audio query, thereby offering the particular melody section of the sound source as a bell sound and/or an RBT according to the personal preference of a user. An audio query input unit(104) inputs a melody section of particular music selected by a user as an audio query. An audio fingerprint extractor(105) extracts audio fingerprints for a music signal outputted from the input unit(104). A music DB(103) indexes meta data of a lot of music and audio fingerprints to store the indexed data and fingerprints. A music recognition and information searcher(106) recognizes music by matching the extracted audio fingerprints with the stored audio fingerprints, and searches meta information of the recognized music. An offset searcher(107) detects a user's preferred particular melody section from the DB(103) for the recognized music. A bell sound and/or RBT generator(108) generates a bell sound and/or an RBT as the detected particular melody section.

Abstract translation: 提供通过实时音乐识别的用户偏好旋律部分的铃声和/或RBT（回铃音）生成系统，以及如果用户输入特定旋律，通过音乐识别来检测声源和偏移位置 作为音频查询的优选声源的部分，从而根据用户的个人喜好将声源的特定旋律部分提供为铃声和/或RBT。 音频查询输入单元（104）输入由用户选择的特定音乐的旋律部分作为音频查询。 音频指纹提取器（105）提取用于从输入单元（104）输出的音乐信号的音频指纹。 音乐DB（103）索引许多音乐和音频指纹的元数据以存储索引的数据和指纹。 音乐识别和信息搜索器（106）通过将所提取的音频指纹与存储的音频指纹进行匹配来识别音乐，并且搜索识别的音乐的元信息。 偏移搜索器（107）从DB（103）中检测出用于所识别的音乐的用户优选的特定旋律部分。 钟声和/或RBT发生器（108）产生铃声和/或RBT作为检测到的特定旋律部分。