Related papers: Diff-MSTC: A Mixing Style Transfer Prototype for C…
The computational benefits of iterative non-autoregressive transformers decrease as the number of decoding steps increases. As a remedy, we introduce Distill Multiple Steps (DiMS), a simple yet effective distillation technique to decrease…
Learning from noisy data has become essential for adapting deep learning models to real-world applications. Traditional methods often involve first evaluating the noise and then applying strategies such as discarding noisy samples,…
Deep representation learning offers a powerful paradigm for mapping input data onto an organized embedding space and is useful for many music information retrieval tasks. Two central methods for representation learning include deep metric…
Localizing a moving sound source in the real world involves determining its direction-of-arrival (DOA) and distance relative to a microphone. Advancements in DOA estimation have been facilitated by data-driven methods optimized with large…
We explore two approaches to creatively altering vocal timbre using Differentiable Digital Signal Processing (DDSP). The first approach is inspired by classic cross-synthesis techniques. A pretrained DDSP decoder predicts a filter for a…
In this paper, we investigate noncoherent multiple-input multiple-output (MIMO) ultra-wideband (UWB) systems where the signal is encoded by differential space-time block code (DSTBC). DSTBC enables noncoherent MIMO UWB systems to achieve…
This paper presents a framework for universal sound separation and polyphonic audio classification, addressing the challenges of separating and classifying individual sound sources in a multichannel mixture. The proposed framework,…
We present MoST (Mixture of Speech and Text), a novel multimodal large language model that seamlessly integrates speech and text processing through our proposed Modality-Aware Mixture of Experts (MAMoE) architecture. While current…
This research project investigates the application of deep learning to timbre transfer, where the timbre of a source audio can be converted to the timbre of a target audio with minimal loss in quality. The adopted approach combines…
Currently, most of existing research in direction of arrival (DOA) estimation is focused on single signal transmission (SST) based signal. However, to make full use of the degree of freedom provided by the system in the polarisation domain,…
Tone style transfer for photo retouching aims to adapt the stylistic tone of the reference image to a given content image. However, the lack of high-quality large-scale triplet datasets with stylized ground truth forces existing methods to…
The disturbance storm time (Dst) index is an important and useful measurement in space weather research. It has been used to characterize the size and intensity of a geomagnetic storm. A negative Dst value means that the Earth's magnetic…
Music mastering style transfer aims to model and apply the mastering characteristics of a reference track to a target track, simulating the professional mastering process. However, existing methods apply fixed processing based on a…
Recent advances in Dynamic Sparse Training (DST) have pushed the frontier of sparse neural network training in structured and unstructured contexts, matching dense-model performance while drastically reducing parameter counts to facilitate…
Knowledge distillation, the technique of transferring knowledge from large, complex models to smaller ones, marks a pivotal step towards efficient AI deployment. Distilling Step-by-Step~(DSS), a novel method utilizing chain-of-thought~(CoT)…
How to learn a better speech representation for end-to-end speech-to-text translation (ST) with limited labeled data? Existing techniques often attempt to transfer powerful machine translation (MT) capabilities to ST, but neglect the…
Style transfer aims to fuse the artistic representation of a style image with the structural information of a content image. Existing methods train specific networks or utilize pre-trained models to learn content and style features.…
Diffusion Policies have become widely used in Imitation Learning, offering several appealing properties, such as generating multimodal and discontinuous behavior. As models are becoming larger to capture more complex capabilities, their…
This study introduces a significant architectural advancement in feature fusion for lyrical content classification by integrating auxiliary structural features directly into the self-attention mechanism of a pre-trained Transformer. I…
Finding well-defined clusters in data represents a fundamental challenge for many data-driven applications, and largely depends on good data representation. Drawing on literature regarding representation learning, studies suggest that one…