Much research in music information retrieval has focused on query-by-humming systems, which search melodic databases using sung queries. The database retrieval aspect of such systems has received considerable attention, but query processing and the melodic representation have not been examined as carefully. Common methods for query processing are based on musical intuition and historical momentum rather than specific performance criteria; existing systems often employ rudimentary note segmentation or coarse quantization of note estimates. In this work, we examine several alternative query processing methods as well as quantized melodic representations. One common difficulty with designing query-by-humming systems is the coupling between system components. We address this issue by measuring the performance of the query processing system both in isolation and coupled with a retrieval system. We first measure the segmentation performance of several note estimators. We then compute the retrieval accuracy of an experimental query-by-humming system that uses the various note estimators along with varying degrees of pitch and duration quantization. The results show that more advanced query processing can improve both segmentation performance and retrieval performance, although the best segmentation performance does not necessarily yield the best retrieval performance. Further, coarsely quantizing the melodic representation generally degrades retrieval accuracy.

With the growing prevalence of large databases of multimedia content, methods for facilitating rapid browsing of such databases or the results of a database search are becoming increasingly important. However, these methods are necessarily media dependent. We present a system for producing short, representative samples (or "audio thumbnails") of selections of popular music. The system searches for structural redundancy within a given song with the aim of identifying something like a chorus or refrain. To isolate a useful class of features for performing such structure-based pattern recognition, we present a development of the chromagram, a variation on traditional time-frequency distributions that seeks to represent the cyclic attribute of pitch perception, known as chroma. The pattern recognition system itself employs a quantized chromagram that represents the spectral energy at each of the 12 pitch classes. We evaluate the system on a database of popular music and score its performance against a set of "ideal" thumbnail locations. Overall performance is found to be quite good, with the majority of errors resulting from songs that do not meet our structural assumptions.

In this paper, we present a spectrum-based system for singer identification that operates for the ideal case in which audio samples contain only the singer's voice. Our method begins with the computation of a robust estimate of the spectral envelope called the composite transfer function (CTF). The CTF is derived from the instantaneous amplitude and frequency of the sinusoidal partials which make up the vocal signal. Unlike traditional source-filter theory , the CTF does not explicitly separate the spectral characteristics of the vocal source and the vocal tract filter. The principal components of the CTFs are used as features for a quadratic classifier to identify singers. The approach is validated on a database containing samples from twelve classically trained singers. In cross validation experiments, test set accuracies of approximately 95% are found for a baseline case. The classifier's performance is not degraded when different vowels are included in classifier training and evaluation. Restricting the frequency range of the CTFs and using a test set containing samples extracted from solo performances of Italian arias reduces the test set accuracy to 70-80%.