CAJ | 학술논문

通过研究哼唱旋律基频提取和检索算法，给出了一个完整的基于哼唱的音乐检索系统框架。系统主要分析了旋律特征提取和近似旋律匹配部分。旋律特征提取部分采用基于差分Mel倒谱法求基频；旋律匹配部分对经典的动态时间弯折算法原理分析后，根据声音特征引入音长差序列的余弦相似度，提高了检索效率和精度。在340首MIDI歌曲的测试集上，前三位识别效率提高3.7%，用时降低16%，系统的性能有明显改善。
통과연구형창선률기빈제취화검색산법，급출료일개완정적기우형창적음악검색계통광가。계통주요분석료선률특정제취화근사선률필배부분。선률특정제취부분채용기우차분Mel도보법구기빈；선률필배부분대경전적동태시간만절산법원리분석후，근거성음특정인입음장차서렬적여현상사도，제고료검색효솔화정도。재340수MIDI가곡적측시집상，전삼위식별효솔제고3.7%，용시강저16%，계통적성능유명현개선。
Through analyzing the humming melodies pitch extraction and retrieval algorithm, a complete system framework of Query By Humming(QBH)is proposed. It includes the melody feature extraction and approximate melody matching in MIDI music database. The Mel Frequency Cepstral Coefficients(MFCC)is extracted. Through analyzing the theory of DTW algorithm, the cosine similarity of the delta duration sequence is added with the characteristics of the sound for per-formance improvement of the system. Experiments are conducted in a test set of 340 MIDI songs. The system gets a success rate of top-3 increased by 3.7%and a 16%time reduction.