本文關(guān)鍵詞： 音高提取 音符切分 音樂自動(dòng)轉(zhuǎn)寫 視唱評(píng)價(jià)　出處：《清華大學(xué)學(xué)報(bào)(自然科學(xué)版)》2011年12期 　論文類型：期刊論文

【摘要】：歌唱聲音的自動(dòng)標(biāo)注是基于內(nèi)容的音樂分析和檢索領(lǐng)域的基礎(chǔ)問題。該文在統(tǒng)計(jì)分析漢語(yǔ)歌唱聲音聲韻母時(shí)長(zhǎng)和音高特征的基礎(chǔ)上,提出了一種聲樂自動(dòng)標(biāo)注模型。該模型將信號(hào)處理、語(yǔ)音學(xué)和音樂知識(shí)結(jié)合,通過韻母-樂譜音高對(duì)齊和基于聲母時(shí)長(zhǎng)分布的邊界優(yōu)化算法實(shí)現(xiàn)了高精度的音符切分。音高提取算法在移調(diào)檢測(cè)的基礎(chǔ)上,通過限定基音周期搜索范圍的策略克服了信號(hào)頻譜中半頻/倍頻點(diǎn)的干擾。結(jié)合音樂教學(xué)實(shí)踐,通過檢測(cè)音符內(nèi)部最穩(wěn)定音高成分、估計(jì)演唱速率和歸一化音符時(shí)長(zhǎng)的方法提取歌唱聲音的音高、節(jié)奏和時(shí)長(zhǎng)信息,并基于這3個(gè)客觀物理量提出了一個(gè)視唱評(píng)價(jià)方法。實(shí)驗(yàn)表明,該文提出的算法能夠準(zhǔn)確地標(biāo)注歌唱聲音中的音符邊界(平均誤差26ms)和音高(平均誤差0.23半音)。
[Abstract]:The automatic tagging of singing sounds is the basic problem in the field of content-based music analysis and retrieval. A vocal automatic tagging model is proposed, which combines signal processing, phonetics and music knowledge. High precision note segmentation is realized by using vowel-music pitch alignment and boundary optimization algorithm based on initial time distribution. Pitch extraction algorithm is based on shift detection. By limiting the search range of pitch period, the interference of half frequency / double frequency point in the signal spectrum is overcome. In combination with music teaching practice, the most stable pitch components within the notes are detected. The method of estimating singing rate and normalized note duration is used to extract the pitch, rhythm and duration information of singing sound. Based on these three objective physical quantities, a method for evaluating the singing performance is proposed. The experimental results show that, The algorithm proposed in this paper can accurately label the note boundary (average error 26ms) and pitch (average error 0.23 semitones) in singing sound.
【作者單位】： 清華大學(xué)計(jì)算機(jī)科學(xué)與技術(shù)系;西北師范大學(xué)物理與電子工程學(xué)院;
【基金】：國(guó)家自然科學(xué)基金資助項(xiàng)目(60928005,60910130)
【分類號(hào)】：J619;TN912.3
，

本文編號(hào)：1534339