Electronic Engineering and Computer Science
Browse by
Recent Submissions
-
Eliciting perspectives on remote healthcare delivery from service users with psychosis in the community: a cross-sectional survey study.
(Frontiers Media, 2024-02-13)INTRODUCTION: The transition towards remote healthcare has been rapidly accelerated in recent years due to a number of factors, including the COVID-19 pandemic, however, few studies have explored service users' views of ... -
MIDI-to-Tab: Guitar Tablature Inference via Masked Language Modeling
(2024-11-10)Guitar tablatures enrich the structure of traditional music notation by assigning each note to a string and fret of a guitar in a particular tuning, indicating precisely where to play the note on the instrument. The problem ... -
GAPS: A Large and Diverse Classical Guitar Dataset and Benchmark Transcription Model
(2024-11-10)We introduce GAPS (Guitar-Aligned Performance Scores), a new dataset of classical guitar performances, and a benchmark guitar transcription model that achieves state-of-the-art performance on GuitarSet in both supervised ... -
NoiseBox: Towards More Efficient and Effective Learning with Noisy Labels
(Institute of Electrical and Electronics Engineers, 2024) -
Differentiable All-pole Filters for Time-varying Audio Systems
(2024)Infinite impulse response filters are an essential building block of many time-varying audio systems, such as audio effects and synthesisers. However, their recursive structure impedes end-toend training of these systems ... -
MSTRE-NET: MULTISTREAMING ACOUSTIC MODELING FOR AUTOMATIC LYRICS TRANSCRIPTION
(ISMIR, 2021-01-01)This paper makes several contributions to automatic lyrics transcription (ALT) research. Our main contribution is a novel variant of the Multistreaming Time-Delay Neural Network (MTDNN) architecture, called MSTRE-Net, which ... -
Computational Pronunciation Analysis in Sung Utterances
(arXiv, 2021-06-21)Recent automatic lyrics transcription (ALT) approaches focus on building stronger acoustic models or indomain language models, while the pronunciation aspect is seldom touched upon. This paper applies a novel computatio ... -
Pitch-Informed Instrument Assignment using a Deep Convolutional Network with Multiple Kernel Shapes.
(arXiv, 2021)This paper proposes a deep convolutional neural network for performing note-level instrument assignment. Given a polyphonic multi-instrumental music signal along with its ground truth or predicted notes, the objective ... -
Posterior Variance-Parameterised Gaussian Dropout: Improving Disentangled Sequential Autoencoders for Zero-Shot Voice Conversion
(Institute of Electrical and Electronics Engineers (IEEE), 2024-04-14)The class of disentangled sequential auto-encoders factorises speech into time-invariant (global) and time-variant (local) representations for speaker identity and linguistic content, respectively. Many of the existing ... -
Unsupervised Pitch-Timbre Disentanglement of Musical Instruments Using a Jacobian Disentangled Sequential Autoencoder
(Institute of Electrical and Electronics Engineers (IEEE), 2024-04-14) -
Structure-Aware Audio-to-Score Alignment using Progressively Dilated Convolutional Neural Networks
(IEEE, 2021-01-31)The identification of structural differences between a music performance and the score is a challenging yet integral step of audio-to-score alignment, an important subtask of music information retrieval. We present a novel ... -
ChatMusician: Understanding and Generating Music Intrinsically with LLM
(2024-08-11)While Large Language Models (LLMs) demonstrate impressive capabilities in text generation, we find that their ability has yet to be generalized to music, humanity’s creative language. We introduce ChatMusician, an open-source ... -
Automatic Generation of Expressive Piano Miniatures
(International Conference on Computational Creativity (ICCC), 2024)We describe an approach to the automatic generation of short piano compositions known as miniatures. At the heart of this is a transformer model which produces expressive performances of miniatures which are then transcribed ... -
Bilinear Models of Parts and Appearances in Generative Adversarial Networks.
(IEEE, 2024-06-26)Recent advances in the understanding of Generative Adversarial Networks (GANs) have led to remarkable progress in visual editing and synthesis tasks, capitalizing on the rich semantics that are embedded in the latent spaces ... -
DiffusionAct: Controllable Diffusion Autoencoder for One-shot Face Reenactment.
(2024)Video-driven neural face reenactment aims to synthesize realistic facial images that successfully preserve the identity and appearance of a source face, while transferring the target head pose and facial expressions. ...