A. James Clark School of Engineering
Permanent URI for this communityhttp://hdl.handle.net/1903/1654
The collections in this community comprise faculty research works, as well as graduate theses and dissertations.
Browse
2 results
Search Results
Item AVISARME: Audio Visual Synchronization Algorithm for a Robotic Musician Ensemble(2012) Berman, David Ross; Chopra, Nikhil; Mechanical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)This thesis presents a beat detection algorithm which combines both audio and visual inputs to synchronize a robotic musician to its human counterpart. Although there has been considerable work done to create sophisticated methods for audio beat detection, the visual aspect of musicianship has been largely ignored. With advancements in image processing techniques, as well as both computer and imaging technologies, it has recently become feasible to integrate visual inputs into beat detection algorithms. Additionally, the proposed method for audio tempo detection also attempts to solve many issues that are present in current algorithms. Current audio-only algorithms have imperfections, whether they are inaccurate, too computationally expensive, or suffer from terrible resolution. Through further experimental testing on both a popular music database and simulated music signals, the proposed algorithm performed statistically better in both accuracy and robustness than the baseline approaches. Furthermore, the proposed approach is extremely efficient, taking only 45ms to compute on a 2.5s signal, and maintains an extremely high temporal resolution of 0.125 BPM. The visual integration also relies on Full Scene Tracking, allowing it to be utilized for live beat detection for practically all musicians and instruments. Numerous optimization techniques have been implemented, such as pyramidal optimization (PO) and clustering techniques which are presented in this thesis. A Temporal Difference Learning approach to sensor fusion and beat synchronization is also proposed and tested thoroughly. This TD learning algorithm implements a novel policy switching criterion which provides a stable, yet quickly reacting estimation of tempo. The proposed algorithm has been implemented and tested on a robotic drummer to verify the validity of the approach. The results from testing are documented in great detail and compared with previously proposed approaches.Item Sparse and Nonnegative Factorizations For Music Understanding(2011) Tjoa, Steven Kiemyang; Liu, K. J. Ray; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)In this dissertation, we propose methods for sparse and nonnegative factorization that are specifically suited for analyzing musical signals. First, we discuss two constraints that aid factorization of musical signals: harmonic and co-occurrence constraints. We propose a novel dictionary learning method that imposes harmonic constraints upon the atoms of the learned dictionary while allowing the dictionary size to grow appropriately during the learning procedure. When there is significant spectral-temporal overlap among the musical sources, our method outperforms popular existing matrix factorization methods as measured by the recall and precision of learned dictionary atoms. We also propose co-occurrence constraints -- three simple and convenient multiplicative update rules for nonnegative matrix factorization (NMF) that enforce dependence among atoms. Using examples in music transcription, we demonstrate the ability of these updates to represent each musical note with multiple atoms and cluster the atoms for source separation purposes. Second, we study how spectral and temporal information extracted by nonnegative factorizations can improve upon musical instrument recognition. Musical instrument recognition in melodic signals is difficult, especially for classification systems that rely entirely upon spectral information instead of temporal information. Here, we propose a simple and effective method of combining spectral and temporal information for instrument recognition. While existing classification methods use traditional features such as statistical moments, we extract novel features from spectral and temporal atoms generated by NMF using a biologically motivated multiresolution gamma filterbank. Unlike other methods that require thresholds, safeguards, and hierarchies, the proposed spectral-temporal method requires only simple filtering and a flat classifier. Finally, we study how to perform sparse factorization when a large dictionary of musical atoms is already known. Sparse coding methods such as matching pursuit (MP) have been applied to problems in music information retrieval such as transcription and source separation with moderate success. However, when the set of dictionary atoms is large, identification of the best match in the dictionary with the residual is slow -- linear in the size of the dictionary. Here, we propose a variant called approximate matching pursuit (AMP) that is faster than MP while maintaining scalability and accuracy. Unlike MP, AMP uses an approximate nearest-neighbor (ANN) algorithm to find the closest match in a dictionary in sublinear time. One such ANN algorithm, locality-sensitive hashing (LSH), is a probabilistic hash algorithm that places similar, yet not identical, observations into the same bin. While the accuracy of AMP is comparable to similar MP methods, the computational complexity is reduced. Also, by using LSH, this method scales easily; the dictionary can be expanded without reorganizing any data structures.