Toward intelligent music information retrieval

Efficient and intelligent music information retrieval is a very important topic of the 21st century. With the ultimate goal of building personal music information retrieval systems, this paper studies the problem of intelligent music information retrieval. Huron points out that since the preeminent functions of music are social and psychological, the most useful characterization would be based on four types of information: genre, emotion, style,and similarity. This paper introduces Daubechies Wavelet Coefficient Histograms (DWCH)for music feature extraction for music information retrieval. The histograms are computed from the coefficients of the db/sub 8/ Daubechies wavelet filter applied to 3 s of music. A comparative study of sound features and classification algorithms on a dataset compiled by Tzanetakis shows that combining DWCH with timbral features (MFCC and FFT), with the use of multiclass extensions of support vector machine,achieves approximately 80% of accuracy, which is a significant improvement over the previously known result on this dataset. On another dataset the combination achieves 75% of accuracy. The paper also studies the issue of detecting emotion in music. Rating of two subjects in the three bipolar adjective pairs are used. The accuracy of around 70% was achieved in predicting emotional labeling in these adjective pairs. The paper also studies the problem of identifying groups of artists based on their lyrics and sound using a semi-supervised classification algorithm. Identification of artist groups based on the Similar Artist lists at All Music Guide is attempted. The semi-supervised learning algorithm resulted in nontrivial increases in the accuracy to more than 70%. Finally, the paper conducts a proof-of-concept experiment on similarity search using the feature set.     

Toward an understanding of the history and impact of user studies in music information retrieval

Most Music Information Retrieval (MIR) researchers will agree that understanding users’ needs and behaviors is critical for developing a good MIR system. The number of user studies in the MIR domain has been gradually increasing since the early 2000s, reflecting this growing appreciation of the need for empirical studies of users. However, despite the growing number of user studies and the wide recognition of their importance, it is unclear how great their impact has been in the field: on how systems are developed, how evaluation tasks are created, and how MIR system developers in particular understand critical concepts such as music similarity or music mood. In this paper, we present our analysis on the growth, publication and citation patterns, topics, and design of 198 user studies. This is followed by a discussion of a number of issues/challenges in conducting MIR user studies and distributing the research results. We conclude by making recommendations to increase the visibility and impact of user studies in the field.     

Predicting user demographics from music listening information

Online activities such as social networking, online shopping, and consuming multi-media create digital traces, which are often analyzed and used to improve user experience and increase revenue, e. g., through better-fitting recommendations and more targeted marketing. Analyses of digital traces typically aim to find user traits such as age, gender, and nationality to derive common preferences. We investigate to which extent the music listening habits of users of the social music platform Last.fm can be used to predict their age, gender, and nationality. We propose a feature modeling approach building on Term Frequency-Inverse Document Frequency (TF-IDF) for artist listening information and artist tags combined with additionally extracted features. We show that we can substantially outperform a baseline majority voting approach and can compete with existing approaches. Further, regarding prediction accuracy vs. available listening data we show that even one single listening event per user is enough to outperform the baseline in all prediction tasks. We also compare the performance of our algorithm for different user groups and discuss possible prediction errors and how to mitigate them. We conclude that personal information can be derived from music listening information, which indeed can help better tailoring recommendations, as we illustrate with the use case of a music recommender system that can directly utilize the user attributes predicted by our algorithm to increase the quality of it’s recommendations.

     

Note segmentation and quantization for music information retrieval

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.     

Evaluating information retrieval system performance based on user preference

One of the challenges of modern information retrieval is to rank the most relevant documents at the top of the large system output. This calls for choosing the proper methods to evaluate the system performance. The traditional performance measures, such as precision and recall, are based on binary relevance judgment and are not appropriate for multi-grade relevance. The main objective of this paper is to propose a framework for system evaluation based on user preference of documents. It is shown that the notion of user preference is general and flexible for formally defining and interpreting multi-grade relevance. We review 12 evaluation methods and compare their similarities and differences. We find that the normalized distance performance measure is a good choice in terms of the sensitivity to document rank order and gives higher credits to systems for their ability to retrieve highly relevant documents.     

An attempt to enhance performance in user session based information retrieval

The ongoing surge in the amount of online information has made the process of accurate retrieval much more difficult. Providers of information retrieval systems have come under a lot of pressure to improve their techniques to cater for the modern user. Conventional systems are often limited as they fail to understand the true search intent of the user. This is usually a result of both poor query formulation by the user and an inability of the search engine to process the query adequately. In this paper, an approach is presented that attempts to learn a user’s short-term interests through the clustering of their search results. A profile is maintained for each user to assist in the process of context resolution for a given query. The details of such an approach and experimental results to evaluate its effectiveness are presented in this paper.     

An effective music information retrieval method using three-dimensional continuous DP

This paper describes a music information retrieval system that uses humming as the key for retrieval. Humming is an easy way for a user to input a melody. However, there are several problems with humming that degrade the retrieval of information. One problem is the human factor. Sometimes, people do not sing accurately, especially if they are inexperienced or unaccompanied. Another problem arises from signal processing. Therefore, a music information retrieval method should be sufficiently robust to surmount various humming errors and signal processing problems. A retrieval system has to extract the pitch from the user's humming. However, pitch extraction is not perfect. It often captures half or double pitches, which are harmonic frequencies of the true pitch, even if the extraction algorithms take the continuity of the pitch into account. Considering these problems, we propose a system that takes multiple pitch candidates into account. In addition to the frequencies of the pitch candidates, the confidence measures obtained from their powers are taken into consideration as well. We also propose the use of an algorithm with three dimensions that is an extension of the conventional Dynamic Programming (DP)algorithm, so that multiple pitch candidates can be treated. Moreover, in the proposed algorithm, DP paths are changed dynamically to take deltaPitches and IOIratios (inter-onset-interval) of input and reference notes into account in order to treat notes being split or unified. We carried out an evaluation experiment to compare the proposed system with a conventional system . When using three-pitch candidates with conference measure and IOI features, the top-ten retrieval accuracy was 94.1%. Thus, the proposed method gave a better retrieval performance than the conventional system.     

A visual user interface for map information retrieval based onsemantic significance

User-interface facilities of a map information system HI-MAP that provide visual feedback to the user are presented. The facilities include semantic panning and zooming, overlaying of thematic maps, etc., and are available through an interactive menu system. HI-MAP retrieves map elements in a specified region on the basis of their relevance and their categorical classification. It has a data structure that includes logical and physical hierarchies for the management of semantic relationships and graphic map elements. The software for implementing these facilities is well modularized, and a variety of interfacing modes can be realized by simple communication between modules. The system contributes toward a reduction of the difficulties in obtaining what is really required from databases     

Capturing the workflows of music information retrieval for repeatability and reuse

Many solutions for the reuse and re-purposing of Music Information Retrieval (MIR) methods, and the tools implementing those methods, have been introduced over recent years. Proposals for achieving interoperability between systems have ranged from shared software libraries and interfaces, through common frameworks and portals, to standardised file formats and metadata. Here we assess these solutions for their suitability to be reused and combined as repurposable components within assemblies (or workflows) that can be used in novel and possibly more ambitious ways. Reuse and repeatability also have great implications for the process of MIR research: the encapsulation of any algorithm and its operation—including inputs, parameters, and outputs—is fundamental to the repeatability and reproducibility of an experiment. This is desirable both for the open and reliable evaluation of algorithms and for the advancement of MIR by building more effectively upon prior research. At present there is no clear best practice widely adopted by the field. Based upon our analysis of contemporary systems and their adoption we reflect as to whether this should be considered a failure. Are there limits to interoperability unique to MIR, and how might they be overcome? Beyond workflows how much research context can, and should, be captured? We frame our assessment within the emerging notion of Research Objects for reproducible research in other domains, and describe how their adoption could serve as a route to reuse in MIR.     

基于Internet的个性化信息检索技术的研究

对搜索引擎个性化模式的提取方式进行了分类探讨,对当今流行的个性化检索技术进行了分类比较,指出了它们的特点差别;最后在此基础上讨论搜索引擎个性化技术所面临的问题以及其发展趋势。     

Contextual music information retrieval and recommendation: State of the art and challenges

Increasing amount of online music content has opened new opportunities for implementing new effective information access services–commonly known as music recommender systems–that support music navigation, discovery, sharing, and formation of user communities. In the recent years a new research area of contextual (or situational) music recommendation and retrieval has emerged. The basic idea is to retrieve and suggest music depending on the user’s actual situation, for instance emotional state, or any other contextual conditions that might influence the user’s perception of music. Despite the high potential of such idea, the development of real-world applications that retrieve or recommend music depending on the user’s context is still in its early stages. This survey illustrates various tools and techniques that can be used for addressing the research challenges posed by context-aware music retrieval and recommendation. This survey covers a broad range of topics, starting from classical music information retrieval (MIR) and recommender system (RS) techniques, and then focusing on context-aware music applications as well as the newer trends of affective and social computing applied to the music domain.     

An investigation of user attitudes toward search engines as an information retrieval tool

After the Internet has gained great popularity at homes and schools, there is much information on the Web. Today, one of the primary uses of the Internet is information retrieval from search engines. The main purpose of the current study is to develop and examine an individual attitude model towards search engines as a tool for retrieving information. This model integrates individual computer experience with perceptions. In addition, it also combines perception theories, such as technology acceptance model (TAM) and motivation, in order to understand individual attitudes toward search engines. The results show that individual computer experience, quality of search systems, motivation, and perceptions of technology acceptance are all key factors that affect individual feelings to use search engines as an information retrieval tool.     

Adaptive content-based music retrieval system

This paper presents a tunable content-based music retrieval (CBMR) system suitable the for retrieval of music audio clips. The audio clips are represented as extracted feature vectors. The CBMR system is expert-tunable by altering the feature space. The feature space is tuned according to the expert-specified similarity criteria expressed in terms of clusters of similar audio clips. The main goal of tuning the feature space is to improve retrieval performance, since some features may have more impact on perceived similarity than others. The tuning process utilizes our genetic algorithm. The R-tree index for efficient retrieval of audio clips is based on the clustering of feature vectors. For each cluster a minimal bounding rectangle (MBR) is formed, thus providing objects for indexing. Inserting new nodes into the R-tree is efficiently performed because of the chosen Quadratic Split algorithm. Our CBMR system implements the point query and the n-nearest neighbors query with the O(logn) time complexity. Different objective functions based on cluster similarity and dissimilarity measures are used for the genetic algorithm. We have found that all of them have similar impact on the retrieval performance in terms of precision and recall. The paper includes experimental results in measuring retrieval performance, reporting significant improvement over the untuned feature space.     

个性化图像检索中用户兴趣模型的构建方法

针对个性化图像检索的语义鸿沟问题,提出了一种新的用户兴趣模型的构建方法。将用户兴趣模型分为长期兴趣和短期兴趣：用户的短期兴趣由图像的低层特征映射得到;用户的长期兴趣经过推理机推理,将短期兴趣映射为高层语义得到,从而弥补语义鸿沟。实验结果表明,经过用户兴趣模型过滤的图像检索结果符合用户的个性化要求,相比已有方法在查准率和查全率上取得了明显的改善。     

Knowledge-based information retrieval

A knowledge-based system is used as a front-end to a very large database to increase the relevance of the information being retrieved. The subject domain of the data base is modelled in a semantic network and the queries to the database are expanded according to the semantic model. An experiment has been performed on a bibliographic database, by developing the prototype KNOWIT, a knowledge-based front-end to the information retrieval system ESA-QUEST¹. An experimental evaluation shows that the number of relevant bibliographic references retrieved with the knowledge-based front-end is significantly improved, without compromising the precision of the retrieval.