Massey Documents by Type

Permanent URI for this communityhttps://mro.massey.ac.nz/handle/10179/294

Browse

Subject: search.filters.subject.460707 Sound and music computing

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Enabling Ableton : facilitating music technology in secondary music education through Discholars : an exegesis presented in partial fulfilment of the requirements of the degree of Master of Creative Enterprise at Massey University, Wellington, New Zealand
    (Massey University, 2019) Campbell, Callum
    Discholars is a company designed to enhance and modernise music education in New Zealand by offering tuition in digital and electronic instruments. It was founded in response to the ubiquity of music technology in the music industry and the opportunity that provides for music education. The creative focus of this research has been to build a curriculum to teach music using a digital audio workstation (DAW) as the primary instrument. Through a series of structured lesson plans, this curriculum teaches musical concepts and production techniques. It incorporates modern research in music pedagogy and is designed to align with the New Zealand curriculum. Discholars' mission is to empower students to express themselves musically as a result of music technology tuition.
  • Thumbnail Image
    Item
    Knobs and nodes : a study of UI design in audio plugins : an exegesis presented in partial fulfilment of the requirements for the degree of Master's in Creative Enterprise at Massey University, Wellington, New Zealand
    (Massey University, 2019) McGregor, Jonathan Peter
    Knobs and Nodes explores how alternate user interfaces influence the use of audio plugins in music production. This idea was investigated through the development and user testing of audio plugins with node-based user interfaces. The Nodal Plugin Duo, comprises two unique audio plugins which exhibit delay and reverb digital signal processing. Once developed, these plugins were tested by music producers, sound designers, and composers in their native creative environments to provide insight on the usability and interactivity of the Nodal Plugin Duo.
  • Thumbnail Image
    Item
    Machine learning and audio processing : a thesis presented in partial fulfilment of the requirements for the degree of Doctor of Philosophy in Computer Science at Massey University, Albany, Auckland, New Zealand
    (Massey University, 2019) Ma, Junbo
    In this thesis, we addressed two important theoretical issues in deep neural networks and clustering, respectively. Also, we developed a new approach for polyphonic sound event detection, which is one of the most important applications in the audio processing area. The developed three novel approaches are: (i) The Large Margin Recurrent Neural Network (LMRNN), which improves the discriminative ability of original Recurrent Neural Networks by introducing a large margin term into the widely used cross-entropy loss function. The developed large margin term utilises the large margin discriminative principle as a heuristic term to navigate the convergence process during training, which fully exploits the information from data labels by considering both target category and competing categories. (ii) The Robust Multi-View Continuous Subspace Clustering (RMVCSC) approach, which performs clustering on a common view-invariant subspace learned from all views. The clustering result and the common representation subspace are simultaneously optimised by a single continuous objective function. In the objective function, a robust estimator is used to automatically clip specious inter-cluster connections while maintaining convincing intra-cluster correspondences. Thus, the developed RMVCSC can untangle heavily mixed clusters without pre-setting the number of clusters. (iii) The novel polyphonic sound event detection approach based on Relational Recurrent Neural Network (RRNN), which utilises the relational reasoning ability of RRNNs to untangle the overlapping sound events across audio recordings. Different from previous works, which mixed and packed all historical information into a single common hidden memory vector, the developed approach allows historical information to interact with each other across an audio recording, which is effective and efficient in untangling the overlapping sound events. All three approaches are tested on widely used datasets and compared with recently published works. The experimental results have demonstrated the effectiveness and efficiency of the developed approaches.