以旋律及歌詞資訊改良哼唱選歌及其GPU加速

Improving Query-by-Singing/Humming by Using Melody and Lyric Information, with GPU Acceleration

王崇喆(Chung-Che Wang)

指導教授 ： 張智星 ； 張俊盛

國立清華大學/電機資訊學院/資訊工程學系所/博士(2017年)

摘要

本論文對於哼唱選歌進行了加速與準確度的改良。我們提出了同時使用旋律和歌詞的資訊的方法。首先會進行哼唱分辨，以將「唱」和「哼」分離開來。對於「哼」的查詢，我們套用了只使用音高資訊的旋律辨識方法；對於「唱」的查詢，我們將旋律距離和歌詞相似度的結果合併，以利用額外的歌詞資訊。本論文中也使用了圖形處理器來進行加速旋律辨識的部分，我們選擇最耗時的資料庫比對部分來加速，並嘗試不同的平行方式以達效能最佳化。

關鍵字

結合旋律距離與歌詞相似度 ； 哼唱選歌 ； 哼唱分辨 ； 圖形處理器加速

並列摘要

This thesis proposes the acceleration and accuracy improvement of a query-by-singing/humming system. We use both melody and lyrics information to achieve better accuracy for query-by-singing/humming. Singing/humming discrimination is first performed to distinguish singing from humming queries. For a humming query, we apply a pitch-only melody recognition method. For a singing query, on the other hand, we combine melody distance and lyrics similarity to take the advantage of extra lyrics information. We also use graphical processing units to accelerate the melody recognition module. We choose to accelerate database comparison, the most time-consuming component of the system, and try different methods to optimize the performance.

並列關鍵字

combined melody distance and lyric similarity ； query-by-singing/humming (QBSH) ； singing/humming discrimination (SHD) ； GPU acceleration

參考文獻

[5] T. Wang, D.-J. Kim, K.-S. Hong, and J.-S. Youn, “Music Information Retrieval System using Lyrics and Melody Information,” in Asia-Pacific Conference on Information Processing, pp. 601-604, 2009.

[7] J.-S. R. Jang, H.-R. Lee, M.-Y. Kao, “Content-based Music Retrieval Using Linear Scaling and Branch-and-Bound Tree search,” in Proc. IEEE International Conference on Multimedia and Expo, August 2001.

[10] J.-C. Chen, J.-S. R. Jang, “TRUES: Tone Recognition Using Extended Segments,” ACM Transactions on Asian Language Information Processing, No. 10, Vol. 7, Aug 2008.

[12] M. Suzuki, T. Hosoya, A. Ito, and S. Makino, “Music Information Retrieval from a Singing Voice Based on Verification of Recognized Hypotheses,” in Proc. International Society for Music Information Retrieval Conference (ISMIR), 2006.

[15] B. Schuller, G. Rigoll, and M. Lang, “Discrimination of Speech and Monophonic Singing in Continuous Audio Streams Applying Multi-Layer Support Vector Machines,” in Proc. IEEE International Conference on Multimedia and Expo, 2004.