“…Even professional singers do not necessarily present error-free queries to MIR systems [31]- [33], [37], because they may not always recall the theme perfectly. To handle such errors, various approximate matching methods, such as dynamic time warping (DTW) [5], [6], [13], [23], [24], the hidden Markov model [15], [31], and the N-gram model [11], [14], have been developed, with DTW being the most popular. However, due to the considerable computational time required for DTW, several speed-up methods have been proposed [5], [23], [24], [31], so that a large-scale music database can be searched more efficiently.…”