スペクトル包絡保存に基づくNMFによる音源分離  [in Japanese] Separation of music signal sources by NMF based on preservation of spectrum envelope  [in Japanese]

Search this Article

Author(s)

    • 浅川 智瑛 Tomoaki Asakawa
    • 筑波大学大学院システム情報工学研究科 University of Tsukuba Graduate School of Systems and Information Engineering.
    • 浜中 雅俊 Masatoshi Hamanaka
    • 筑波大学大学院システム情報工学研究科|JSTさきがけ University of Tsukuba Graduate School of Systems and Information Engineering. | PRESTO JST

Abstract

本稿では複数の楽器による混合音源をスペクトル包絡保存に基づく NMF によって個別の楽器の音響信号に分離する方法を提案する.我々の手法は近しい音高であればそのスペクトル包絡が周波数方向にシフトするという調波音の一般的な特徴に基づいたものであり,各々の楽器の演奏可能なあらゆる中心周波数において基底を設け,隣接した基底についてその包絡が近似するよう制約を行うことで分離を行う.この操作は各々の楽器の音色を特徴として成分を分離することに相当し,教師なし学習での調波・非調波混合音源の分離を可能とする.性能評価実験として MIDI での混合演奏音源を分離し,SNR を求めた結果リードギターについて約 3.6dB,ドラムについて 6.0dB の分解能を得ることができた.

This paper proposes the method to separate polyphonic music signal into signals of each musical instrument by NMF: Non-negative Matrix Factorization based on preservation of spectrum envelope. Our method bases on a common feature of harmonic signal: spectrum envelopes of musical signal in close pitches played by the harmonic music instrument would be similar. We estimate power spectrums of each instrument by NMF with restriction to synchronize spectrum envelope of bases which are allocated to all possible center frequencies of each instrument. This manipulation means separation of components which refers to tones of each instrument and realizes both of separation without pre-training and separation of signal including harmonic and non-harmonic sound. We had an experiment to decompose mixture sound signal of MIDI instruments into each instrument and evaluated the result by SNR of single MIDI instrument sound signals and separated signals. As a result, SNR of lead guitar and drums approximately marked 3.6 and 6.0 dB and showed significance of our method.

Journal

  • IPSJ SIG Notes

    IPSJ SIG Notes 2014-MUS-102(16), 1-6, 2014-02-16

    Information Processing Society of Japan (IPSJ)

Codes

  • NII Article ID (NAID)
    110009662744
  • NII NACSIS-CAT ID (NCID)
    AN10438388
  • Text Lang
    JPN
  • Data Source
    NII-ELS 
Page Top