In high performance computing systems, object deserialization can become a surprisingly important bottleneck---in our test, a set of general-purpose, highly parallelized applications spends 64% of total execution time deserializing data into objects.This paper presents the Morpheus model, which allows applications to move such computations to a storage device. We use this model to deserialize data into application objects inside storage devices, rather than in the host CPU. Using the Morpheus model for object deserialization avoids unnecessary system overheads, frees up scarce CPU and main memory resources for compute-intensive workloads, saves I/O bandwidth, and reduces power consumption. In heterogeneous, co-processor-equipped systems, Morpheus allows application objects to be sent directly from a storage device to a co-processor (e.g., a GPU) by peer-to-peer transfer, further improving application performance as well as reducing the CPU and main memory utilizations.This paper implements Morpheus-SSD, an SSD supporting the Morpheus model. Morpheus-SSD improves the performance of object deserialization by 1.66×, reduces power consumption by 7%, uses 42% less energy, and speeds up the total execution time by 1.32×. By using NVMe-P2P that realizes peer-to-peer communication between Morpheus-SSD and a GPU, Morpheus-SSD can speed up the total execution time by 1.39× in a heterogeneous computing platform.

Morpheus: creating application objects efficiently for heterogeneous computing

Comunicacio presentada a la 53rd International Conference: Semantic audio, celebrada els dies 27 a 29 de gener de 2014 a Londres, Regne Unit.

Creating Research Corpora for the Computational Study of Music: the case of the CompMusic Project

Ragas are characterized by their melodic motifs or catch phrases that constitute strong cues to the raga identity for both the performer and the listener, and therefore are of great interest in music retrieval and automatic transcription. While the characteristic phrases, or pakads, appear in written notation as a sequence of notes, musicological rules for interpretation of the phrase in performance in a manner that allows considerable creative expression, while not transgressing raga grammar, are not explicitly defined. In this work, machine learning methods are used on labelled databases of Hindustani and Carnatic vocal audio concerts to obtain phrase classification on manually segmented audio. Dynamic time warping and HMM based classification are applied on time series of detected pitch values used for the melodic representation of a phrase. Retrieval experiments on raga-characteristic phrases show promising results while providing interesting insights on the nature of variation in the surface ...

/pdf/classification-of-melodic-motifs-in-raga-music-with-time-27luuwjv9i.pdf

Classification of Melodic Motifs in Raga Music with Time-series Matching

Automatic rĀga recognition is one of the fundamental computational tasks in Indian art music. Motivated by the way seasoned listeners identify rĀgas, we propose a rĀga recognition approach based on melodic phrases. Firstly, we extract melodic patterns from a collection of audio recordings in an unsupervised way. Next, we group similar patterns by exploiting complex networks concepts and techniques. Drawing an analogy to topic modeling in text classification, we then represent audio recordings using a vector space model. Finally, we employ a number of classification strategies to build a predictive model for rĀga recognition. To evaluate our approach, we compile a music collection of over 124 hours, comprising 480 recordings and 40 rĀgas. We obtain 70% accuracy with the full 40-rĀga collection, and up to 92% accuracy with its 10-rĀga subset. We show that phrase-based rĀga recognition is a successful strategy, on par with the state of the art, and sometimes outperforms it. A by-product of our approach, which arguably is as important as the task of rĀga recognition, is the identification of rĀga-phrases. These phrases can be used as a dictionary of semantically-meaningful melodic units for several computational tasks in Indian art music.

/pdf/phrase-based-raga-recognition-using-vector-space-modeling-50ttd4i8d4.pdf

Phrase-based rĀga recognition using vector space modeling

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.

/pdf/automatic-tonic-identification-in-indian-art-music-52sdzhiv4f.pdf

Automatic Tonic Identification in Indian Art Music: Approaches and Evaluation

Melodic motifs form essential building blocks in Indian Classical music. The motifs, or key phrases, provide strong cues to the identity of the underlying raga in both Hindustani and Carnatic styles of Indian music. Thus the automatic detection of such recurring basic melodic shapes from audio is of relevance in music information retrieval. The extraction of melodic attributes from polyphonic audio and the variability inherent in the performance, which does not follow a predefined score, make the task particularly challenging. In this work, we consider the segmentation of selected melodic motifs from audio signals by computing similarity measures on time series of automatically detected pitch values. The methods are investigated in the context of detecting the signature phrase of Hindustani vocal music compositions (bandish) within and across performances.

/pdf/detecting-melodic-motifs-from-audio-for-hindustani-classical-1weah5grgx.pdf

Detecting melodic motifs from audio for hindustani classical music

Melodic motifs form essential building blocks in Indian Classical music. The motifs, or key phrases, provide strong cues to the identity of the underlying raga in both Hindustani and Carnatic styles of Indian music. Automatic identification and clustering of similar motifs is relevant in this context. The inherent variations in various instances of a characteristic phrase in a bandish (composition) performance make it challenging to identify similar phrases in a performance. A nyas svara (long note) marks the ending of these phrases. The proposed method does segmentation of phrases through identification of nyas and computes similarity with the reference characteristic phrase.

/pdf/detection-of-raga-characteristic-phrases-from-hindustani-1x4ah5wmml.pdf

Detection of Raga-characteristic phrases from Hindustani Classical Music Audio

This paper describes serialization support in an object oriented Java processor like jHISC. The relevance of serializing an object confines to situations when an object has to be sent over network or stored as a persistent object. But these are not rare scenarios when an application in a mobile device is considered. This paper proposes a serialization functional unit which consists of a serialization unit and deserialization unit along with descriptors and pool to describe and store serialized objects. This design can enhance the performance of Java based mobile devices which runs applications those communicate with similar applications very often. This design makes use of architectural features of processors like jHISC. This design can contribute much to Java based mobile computing in the near future.

Object serialization support for object oriented java processors

Identifying similarities between ragas in Hindustani music impacts tasks like music recommendation, music information retrieval and automatic analysis of large-scale musical content. Quantifying raga similarity becomes extremely challenging as it demands assimilation of both intrinsic (viz., notes, tempo) and extrinsic (viz. raga singingtime, emotions conveyed) properties of ragas. This paper introduces novel frameworks for quantifying similarities between ragas based on their melodic attributes alone, available in the form of bandish (composition) notation. Based on the hypothesis that notes in a particular raga are characterized by the company they keep, we design and train several deep recursive neural network variants with Long Short-term Memory (LSTM) units to learn distributed representations of notes in ragas from bandish notations. We refer to these distributed representations as note-embeddings. Note-embeddings, as we observe, capture a raga’s identity, and thus the similarity between note-embeddings signifies the similarity between the ragas. Evaluations with perplexity measure and clustering based method show the performance improvement in identifying similarities using note-embeddings over n-gram and unidirectional LSTM baselines. While our metric may not capture similarity between ragas in their entirety, it could be quite useful in various computational music settings that heavily rely on melodic information.

Joe Cheri Ross

Papers

Detecting melodic motifs from audio for hindustani classical music

Classification of Melodic Motifs in Raga Music with Time-series Matching

Detection of Raga-characteristic phrases from Hindustani Classical Music Audio

Object serialization support for object oriented java processors

Identifying Raga Similarity Through Embeddings Learned from Compositions' Notation.