STUDENT'S-t MIXTURE MODEL BASED MULTI-INSTRUMENT RECOGNITION IN POLYPHONIC MUSIC

We address the problem of multi-instrument recognition in polyphonic music signals. Individual instruments are modeled within a stochastic framework using Student's-t Mixture Models (tMMs). We impose a mixture of these instrument models on the polyphonic signal model. No a priori knowledge is assumed about the number of instruments in the polyphony. The mixture weights are estimated in a latent variable framework from the polyphonic data using an Expectation Maximization (EM) algorithm, derived for the proposed approach. The weights are shown to indicate instrument activity. The output of the algorithm is an Instrument Activity Graph (IAG), using which, it is possible to find out the instruments that are active at a given time. An average F-ratio of 0 : 7 5 is obtained for polyphonies containing 2-5 instruments, on a experimental test set of 8 instruments: clarinet, flute, guitar, harp, mandolin, piano, trombone and violin.

Automatic Tonic Identification in Indian Art Music: Approaches and Evaluation

The tonic is a fundamental concept in Indian art music. It is the base pitch, which an artist chooses in order to construct the melodies during a rg(a) rendition, and all accompanying instruments are tuned using the tonic pitch. Consequently, tonic identification is a fundamental task for most computational analyses of Indian art music, such as intonation analysis, melodic motif analysis and rg recognition. In this paper we review existing approaches for tonic identification in Indian art music and evaluate them on six diverse datasets for a thorough comparison and analysis. We study the performance of each method in different contexts such as the presence/absence of additional metadata, the quality of audio data, the duration of audio data, music tradition (Hindustani/Carnatic) and the gender of the singer (male/female). We show that the approaches that combine multi-pitch analysis with machine learning provide the best performance in most cases (90% identification accuracy on average), and are robust across the aforementioned contexts compared to the approaches based on expert knowledge. In addition, we also show that the performance of the latter can be improved when additional metadata is available to further constrain the problem. Finally, we present a detailed error analysis of each method, providing further insights into the advantages and limitations of the methods.

MULTI-INSTRUMENT DETECTION IN POLYPHONIC MUSIC USING GAUSSIAN MIXTURE BASED FACTORIAL HMM

We formulate the problem of detecting the constituent instruments in a polyphonic music piece as a joint decoding problem. From monophonic data, parametric Gaussian Mixture Hidden Markov Models (GM-HMM) are obtained for each instrument. We propose a method to use the above models in a factorial framework, termed as Factorial GM-HMM (F-GM-HMM). The states are jointly inferred to explain the evolution of each instrument in the mixture observation sequence. The dependencies are decoupled using variational inference technique. We show that the joint time evolution of all instruments' states can be captured using F-GM-HMM. We compare performance of proposed method with that of Student's-t mixture model (tMM) and GM-HMM in an existing latent variable framework. Experiments on two to five polyphony with 8 instrument models trained on the RWC dataset, tested on RWC and TRIOS datasets show that F-GM-HMM gives an advantage over the other considered models in segments containing co-occurring instruments.

Espectáculos cortesanos en la América española del siglo XVII : las fiestas como caso para el análisis de la relación entre la Corte y la Corte virreinal

La Corte madrileña de los Austrias, al igual que el resto de las monarquías europeas del siglo XVII, generó una variada gama de fiestas públicas y privadas, como por ejemplo teatro musical, mascaradas y procesiones callejeras en las que desfilaban carros alegóricos con danzantes y músicos. Estos espectáculos no eran un mero entretenimiento sino que estaban destinados a resaltar las virtudes del monarca y a hacer conscientes a los espectadores del lugar que les cabía ocupar en esa sociedad recurriendo para ello a un complejo discurso simbólico. Las Cortes virreinales de América trasladaron a sus territorios estas prácticas que valían, fundamentalmente, para hacer presente la figura del rey y mantener viva la lealtad a la corona. Analizamos dos ejemplos de fiesta, una mascarada celebrada en Pausa (Perú) y un intermedio dramáticomusical en Sucre, que nos revelan la forma de pensamiento, las conductas y la organización de la sociedad cortesana virreinal.

Improving speech transcription for Mandarin-english translation

This paper describes the development of the CU-HTK Mandarin Speech-To-Text (STT) system and assesses its performance as part of a transcription-translation pipeline which converts broadcast Mandarin audio into English text. Recent improvements to the STT system are described and these give Character Error Rate (CER) gains of 14.3% absolute for a Broadcast Conversation (BC) task and 5.1% absolute for a Broadcast News (BN) task. The output of these STT systems is then post-processed, so that it consists of sentence-like segments, and translated into English text using a Statistical Machine Translation (SMT) system. The performance of the transcription-translation pipeline is evaluated using the Translation Edit Rate (TER) and BLEU metrics. It is shown that improving both the STT system and the post-STT segmentations can lower the TER scores by up to 5.3% absolute and increase the BLEU scores by up to 2.7% absolute. © 2007 IEEE.

Ontologies for representation of folk song metadata

The digital management of collections in museums, archives, libraries and galleries is an increasingly important part of cultural heritage studies. This paper describes a representation for folk song metadata, based on the Web Ontology Language (OWL) implementation of the CIDOC Conceptual Reference Model. The OWL representation facilitates encoding and reasoning over a genre ontology, while the CIDOC model enables a representation of complex spatial containment and proximity relations among geographic regions. It is shown how complex queries of folk song metadata, relying on inference and not only retrieval, can be expressed in OWL and solved using a description logic reasoner.

An Analysis of English, Spanish and Basque Demonstratives in Narrative: a Matter of Viewpoint

[EN]This paper undertakes the study of the occurrence of non-corresponding demonstrative forms in Spanish, Basque and English in exactly the same linguistic context. It is proposed that the differenccs in the choice of the demonstratives result from the differences in the kind of iniormation that must be coded in each of the languages. Thus, I will argue that in Spanish and Basque the obligatory coding of the aspectual categories of the imperfect and the preterit has the function of imposing specific viewing arrangements onto the situations they designate. By contrast, in English, where the aspectual distinction is not overtly coded, the demonstrativcs are proposed to fulfil this function.

Internationalisation, multilingualism and English-medium instruction: the teacher's perspective

[EN]In the newEuropean higher education space, Universities in Europe are exhorted to cultivate and develop multilingualism. The European Commission’s 2004–2006 action plan for promoting language learning and diversity speaks of the need to build an environment which is favourable to languages. Yet reality indicates that it is English which reigns supreme and has become the main foreign language used as means of instruction at European universities. Internationalisation has played a key role in this process, becoming one of the main drivers of the linguistic hegemony exerted by English. In this paper we examine the opinions of teaching staff involved in English-medium instruction, from pedagogical ecologyof-language and personal viewpoints. Data were gathered using group discussion. The study was conducted at a multilingual Spanish university where majority (Spanish), minority (Basque) and foreign (English) languages coexist, resulting in some unavoidable linguistic strains. The implications for English-medium instruction are discussed at the end of this paper.

Music-Theoretic Estimation of Chords and Keys from Audio

This paper proposes a new method for local key and chord estimation from audio signals. This method relies primarily on principles from music theory, and does not require any training on a corpus of labelled audio files. A harmonic content of the musical piece is first extracted by computing a set of chroma vectors. A set of chord/key pairs is selected for every frame by correlation with fixed chord and key templates. An acyclic harmonic graph is constructed with these pairs as vertices, using a musical distance to weigh its edges. Finally, the sequences of chords and keys are obtained by finding the best path in the graph using dynamic programming. The proposed method allows a mutual chord and key estimation. It is evaluated on a corpus composed of Beatles songs for both the local key estimation and chord recognition tasks, as well as a larger corpus composed of songs taken from the Billboard dataset.