Predictability of music descriptor time series and its application to cover song detection

Intuitively, music has both predictable and unpredictable components. In this work we assess this qualitative statement in a quantitative way using common time series models fitted to state-of-the-art music descriptors. These descriptors cover different musical facets and are extracted from a large collection of real audio recordings comprising a variety of musical genres. Our findings show that music descriptor time series exhibit a certain predictability not only for short time intervals, but also for mid-term and relatively long intervals. This fact is observed independently of the descriptor, musical facet and time series model we consider. Moreover, we show that our findings are not only of theoretical relevance but can also have practical impact. To this end we demonstrate that music predictability at relatively long time intervals can be exploited in a real-world application, namely the automatic identification of cover songs (i.e. different renditions or versions of the same musical piece). Importantly, this prediction strategy yields a parameter-free approach for cover song identification that is substantially faster, allows for reduced computational storage and still maintains highly competitive accuracies when compared to state-of-the-art systems.

A two-stage approach for tonic identification in indian art music

In this paper we propose a new approach for tonic identification in Indian art music and present a proposal for acomplete iterative system for the same. Our method splits the task of tonic pitch identification into two stages. In the first stage, which is applicable to both vocal and instrumental music, we perform a multi-pitch analysis of the audio signal to identify the tonic pitch-class. Multi-pitch analysisallows us to take advantage of the drone sound, which constantlyreinforces the tonic. In the second stage we estimate the octave in which the tonic of the singer lies and is thusneeded only for the vocal performances. We analyse the predominant melody sung by the lead performer in order to establish the tonic octave. Both stages are individually evaluated on a sizable music collection and are shown toobtain a good accuracy. We also discuss the types of errors made by the method.Further, we present a proposal for a system that aims to incrementally utilize all the available data, both audio and metadata in order to identify the tonic pitch. It produces a tonic estimate and a confidence value, and is iterative in nature. At each iteration, more data is fed into the systemuntil the confidence value for the identified tonic is above a defined threshold. Rather than obtain high overall accuracy for our complete database, ultimately our goal is to develop a system which obtains very high accuracy on a subset of the database with maximum confidence.

Applause identification and its relevance to archival of Carnatic music

A Carnatic music concert is made up of a sequence of pieces, where each piece corresponds to a particular genre and ra¯aga (melody). Unlike a western music concert, the artist may be applauded intra-performance inter-performance. Most Carnatic music that is archived today correspond to a single audio recordings of entire concerts.The purpose of this paper is to segment single audio recordings into a sequence of pieces using thecharacteristic features of applause and music. Spectral flux, spectral entropy change quite significantly from music to applause and vice-versa. The characteristics of these features for a subset of concerts was studied. A threshold based approach was used to segment the pieces into music fragments and applauses. Preliminary resultson recordings 19 concerts from matched microphones show that the EER is about 17% for a resolution of 0.25 seconds. Further, a parameter called CUSUM is estimatedfor the applause regions. The CUSUM values determine the strength of the applause. The CUSUM is used to characterise the highlights of a concert.

A method for extracting semantic information from on-line art music discussion forums

In this paper a method for extracting semantic informationfrom online music discussion forums is proposed. The semantic relations are inferred from the co-occurrence of musical concepts in forum posts, using network analysis. The method starts by defining a dictionary of common music terms in an art music tradition. Then, it creates a complex network representation of the online forum by matchingsuch dictionary against the forum posts. Once the complex network is built we can study different network measures, including node relevance, node co-occurrence andterm relations via semantically connecting words. Moreover, we can detect communities of concepts inside the forum posts. The rationale is that some music terms are more related to each other than to other terms. All in all, this methodology allows us to obtain meaningful and relevantinformation from forum discussions.

A Musically aware system for browsing and interacting with audio music collections

In the context of the CompMusic project we are developing methods to automatically describe/annotate audio music recordings pertaining to various music cultures. As away to demonstrate the usefulness of the methods we are also developing a system to browse and interact with specific audio collections. The system is an online web application that interfaces with all the data gathered (audio, scores plus contextual information) and all the descriptions that are automatically generated with the developed methods. In this paper we present the basic architecture of the proposed system, the types of data sources that it includes,and we mention some of the culture specific issues that we are working on for its development. The system is in a preliminary stage but it shows the potential that MIR technologies can have in browsing and interacting with musiccollections of various cultures.

Opportunities for a cultural specific approach in the computational description of music

The current research in Music Information Retrieval (MIR) is showing the potential that the Information Technologies can have in music related applications. Amajor research challenge in that direction is how to automaticallydescribe/annotate audio recordings and how to use the resulting descriptions to discover and appreciate music in new ways. But music is a complex phenomenonand the description of an audio recording has to deal with this complexity. For example, each musicculture has specificities and emphasizes different musicaland communication aspects, thus the musical recordings of each culture should be described differently. At the same time these cultural specificities give us the opportunity to pay attention to musical concepts andfacets that, despite being present in most world musics, are not easily noticed by listeners. In this paper we present some of the work done in the CompMusic project, including ideas and specific examples on how to take advantage of the cultural specificities of differentmusical repertoires. We will use examples from the art music traditions of India, Turkey and China.

Measuring Instruments In Cardiology Adapted Into Portuguese Language Of Brazil: A Systematic Review

This was a systematic review aimed at identifying and characterizing measuring instruments, developed in the context of cardiology, which were adapted into Portuguese language of Brazil. Systematic searches were performed in six databases. Information extracted included cultural adaptation process and measurement properties. To assess the methodological quality of studies, criteria based on international guidelines for cultural adaptation of instruments were used. Among the 114 articles found, 14 were eligible for review. Of these, most evaluated quality of life (35.7%) and health knowledge/learning (28.6%). Most studies followed all stages of the adaptation process recommended in the literature. With respect to measurement properties, internal consistency, verified by Cronbach’s alpha, was the property reported in the majority of the studies, as well as construct and criterion validity. This study is expected to provide to the scientific community a critical evaluation of adapted questionnaires available in the context of cardiology.


Hyperventilation complaints in music performance anxiety among classical music students.

Objective: Despite the importance of respiration and hyperventilation in anxiety disorders, research on breathing disturbances associated with hyperventilation is rare in the field of music performance anxiety (MPA, also known as stage fright). The only comparable study in this area reported a positive correlation between negative feelings of MPA and hyperventilation complaints during performance. The goals of this study were (a) to extend these previous findings to the period before performance, (b) to test whether a positive correlation also exists between hyperventilation complaints and the experience of stage fright as a problem, (c) to investigate instrument-specific symptom reporting, and (d) to confirm gender differences in negative feelings of MPA and hyperventilation complaints reported in other studies. Methods: We assessed 169 university students of classical music with a questionnaire comprising: the State-Trait Anxiety Inventory for negative feelings of MPA, the Nijmegen Questionnaire for hyperventilation complaints, and a single item for the experience of stage fright as a problem. Results: We found a significant positive correlation between hyperventilation complaints and negative feelings of MPA before performance and a significant positive correlation between hyperventilation complaints and the experience of stage fright as a problem. Wind musicians/singers reported a significantly higher frequency of respiratory symptoms than other musicians. Furthermore, women scored significantly higher on hyperventilation complaints and negative feelings of MPA. Conclusion: These results further the findings of previous reports by suggesting that breathing disturbances associated with hyperventilation may play a role in MPA prior to going on stage. Experimental studies are needed to confirm whether hyperventilation complaints associated with negative feelings of MPA manifest themselves at the physiological level. (C) 2010 Elsevier Inc. All rights reserved.

Study of adaptation and validation of the Practice environment scale of the nursing work index for the portuguese reality

Objective: Testing the psychometric properties of the Portuguese version of the Practice Environment Scale of the Nursing Work Index. Method: A descriptive, analytical and cross-sectional study, for the cross-cultural adaptation and validation of the psychometric properties of the scale. The study participants were 236 nurses from two hospitals in the regions of Lisbon and Vale do Tejo. Results: The 0.92 Cronbach’s alpha was obtained for overall reliability and support of a five-dimension structure. Conclusion: The excellent quality of adjustment of analysis confirms the validity of the adapted version to hospital care settings, although there was no total coincidence of items in the five dimensions


Portuguese validation of the Symptom Inventory of the M.D. Anderson Cancer Center

Objective To analyze the reliability and validity of the psychometric properties of the Brazilian version of the instrument for symptom assessment, titled MD Anderson Symptom Inventory - core. Method A cross-sectional study with 268 cancer patients in outpatient treatment, in the municipality of Ijuí, state of Rio Grande do Sul, Brazil. Results The Cronbach’s alpha for the MDASI general, symptoms and interferences was respectively (0.857), (0.784) and (0.794). The factor analysis showed adequacy of the data (0.792). In total, were identified four factors of the principal components related to the symptoms. Factor I: sleep problems, distress (upset), difficulties in remembering things and sadness. Factor II: dizziness, nausea, lack of appetite and vomiting. Factor III: drowsiness, dry mouth, numbness and tingling. Factor IV: pain, fatigue and shortness of breath. A single factor was revealed in the component of interferences with life (0.780), with prevalence of activity in general (59.7%), work (54.9%) and walking (49.3%). Conclusion The Brazilian version of the MD Anderson Symptom Inventory - core showed adequate psychometric properties in the studied population.

Health care to immigrant and Portuguese pregnant women in Portugal

This study aimed to assess the care received and the barriers faced by immigrants and Portuguese pregnant women in Portugal. This is an exploratory qualitative study, resorting to applying semi-structured interviews to 60 immigrant and 22 Portuguese women. Content analysis supported by QSR Nvivo10 program was used. The study was approved by an Ethics Committee. The results showed four categories related to affective dimensions-relational, cognitive, technical-instrumental and health care policy for pregnant women. As for the barriers in health care, these were mentioned by some of the expectant mothers, especially immigrant women. Almost all, both immigrant and Portuguese, pregnant women were satisfied with the health care.

Knowledge of the Portuguese population on Basic Life Support and availability to attend training

OBJECTIVETo evaluate the level of knowledge and the availability of the Portuguese population to attend training in Basic Life Support (BLS) and identify factors related to their level of knowledge about BLS.METHODObservational study including 1,700 people who responded to a questionnaire containing data on demography, profession, training, interest in training and knowledge about BLS.RESULTSAmong 754 men and 943 women, only 17.8% (303) attended a course on BLS, but 95.6% expressed willingness to carry out the training. On average, they did not show good levels of knowledge on basic life support (correct answers in 25.9 ± 11.5 of the 64 indicators). Male, older respondents who had the training and those who performed BLS gave more correct answers, on average (p<0.01).CONCLUSIONThe skill levels of the Portuguese population are low, but people are available for training, hence it is important to develop training courses and practice to improve their knowledge.

Burned-out but proud Portuguese family doctors

Background: Burnout syndrome (BS) is increasing among health professionals, including family doctors (FD). Aim: To characterize the prevalence of BS in a sample of FDs working in the Portuguese National Health System. Design: Cross-sectional survey. Setting: Primary Health Care Centers (HCC) from the 18 continental districts and 2 archipelagos of Portugal. Method: The Portuguese version of the Maslach Burnout Inventory - Human Services Survey (MBI - HSS) was sent to 40 randomly selected health-care centers (HCC) and distributed to the FDs employed. Sociodemographic and work-related data was also collected. Participants were classified as having high, average or low levels of emotional exhaustion (EE), depersonalization (DP) and personal accomplishment (PA) dimensions of burnout. Results: 371 questionnaires were sent, of which 153 (83 women, age range 29-64 years; response rate 41%) returned. One quarter (25.5%) of participants had high EE, 10.1% high DP and 11.4% high PA, but only 2.0% of participants scored high for all three dimensions. Women had significantly higher DP and PA scores than men; increased daily workload also led to increased PA scores. Conversely, no association was found between BS scores and age, marital status, number of years of practice or type of HCC (Family or Personalized). Conclusion: High burnout is relatively common among Portuguese family doctors, yet slightly lower than reported for other European countries. Burnout relief measures should be developed in order to prevent a further increase of BS among Portuguese FDs.