Related papers: On the Pros and Cons of Momentum Encoder in Self-S…
We examine two different techniques for parameter averaging in GAN training. Moving Average (MA) computes the time-average of parameters, whereas Exponential Moving Average (EMA) computes an exponentially discounted sum. Whilst MA is known…
Integrating front-end speech enhancement (SE) models with self-supervised learning (SSL)-based speech models is effective for downstream tasks in noisy conditions. SE models are commonly fine-tuned using SSL representations with mean…
Audio self-supervised learning (SSL) pre-training, which aims to learn good representations from unlabeled audio, has made remarkable progress. However, the extensive computational demands during pre-training pose a significant barrier to…
Several recent works have directly extended the image masked autoencoder (MAE) with random masking into video domain, achieving promising results. However, unlike images, both spatial and temporal information are important for video…
Self-supervised landmark estimation is a challenging task that demands the formation of locally distinct feature representations to identify sparse facial landmarks in the absence of annotated data. To tackle this task, existing…
Melody preservation is crucial in singing voice conversion (SVC). However, in many scenarios, audio is often accompanied with background music (BGM), which can cause audio distortion and interfere with the extraction of melody and other key…
Due to the high communication overhead when training machine learning models in a distributed environment, modern algorithms invariably rely on lossy communication compression. However, when untreated, the errors caused by compression…
Recent advances in LLM-based ASR connect frozen speech encoders with Large Language Models (LLMs) via lightweight projectors. While effective in monolingual settings, a single projector struggles to capture the diverse acoustic-to-semantic…
Self-supervised learning (SSL) has become a popular method for generating invariant representations without the need for human annotations. Nonetheless, the desired invariant representation is achieved by utilising prior online…
Self-supervised learning (SSL) allows training data representations without a supervised signal and has become an important paradigm in machine learning. Most SSL methods employ the cosine similarity between embedding vectors and hence…
Speech Self-Supervised Learning (SSL) has demonstrated considerable efficacy in various downstream tasks. Nevertheless, prevailing self-supervised models often overlook the incorporation of emotion-related prior information, thereby…
Music emotion recognition (MER) aims to identify the emotions conveyed in a given musical piece. However, currently, in the field of MER, the available public datasets have limited sample sizes. Recently, segment-based methods for…
Simplicial Embeddings (SEM) are representations learned through self-supervised learning (SSL), wherein a representation is projected into $L$ simplices of $V$ dimensions each using a softmax operation. This procedure conditions the…
Typical deep neural video compression networks usually follow the hybrid approach of classical video coding that contains two separate modules: motion coding and residual coding. In addition, a symmetric auto-encoder is often used as a…
Edge inference for large language models (LLM) offers secure, low-latency, and cost-effective inference solutions. We emphasize that an edge accelerator should achieve high area efficiency and minimize external memory access (EMA) during…
Steered-Mixtures-of-Experts (SMoE) models provide sparse, edge-aware representations, applicable to many use-cases in image processing. This includes denoising, super-resolution and compression of 2D- and higher dimensional pixel data.…
Masked video modeling, such as VideoMAE, is an effective paradigm for video self-supervised learning (SSL). However, they are primarily based on reconstructing pixel-level details on natural videos which have substantial temporal…
An event camera is a novel vision sensor that can capture per-pixel brightness changes and output a stream of asynchronous ``events''. It has advantages over conventional cameras in those scenes with high-speed motions and challenging…
Self-supervised learning (SSL) methods aim to exploit the abundance of unlabelled data for machine learning (ML), however the underlying principles are often method-specific. An SSL framework derived from biological first principles of…
Class-agnostic motion prediction methods aim to comprehend motion within open-world scenarios, holding significance for autonomous driving systems. However, training a high-performance model in a fully-supervised manner always requires…