Related papers: Efficient Supervised Training of Audio Transformer…

Unsupervised representation learning has significantly advanced various machine learning tasks. In the computer vision domain, state-of-the-art approaches utilize transformations like random crop and color jitter to achieve invariant…

Direct speech-to-speech translation (S2ST) models suffer from data scarcity issues as there exists little parallel S2ST data, compared to the amount of data available for conventional cascaded systems that consist of automatic speech…

Pre-training has marked numerous state of the arts in high-level computer vision, while few attempts have ever been made to investigate how pre-training acts in image processing systems. In this paper, we tailor transformer-based…

We present a modular approach to building cascade speech translation (AST) models that guarantees that the resulting model performs no worse than the 1-best cascade baseline while preserving state-of-the-art speech recognition (ASR) and…

Bioacoustic recognition requires fine-grained acoustic understanding to distinguish similar-sounding species. However, many large-scale data repositories such as iNaturalist are weakly annotated, often with only a single positive species…

Deep learning techniques have revolutionised medical imaging, improving diagnostic accuracy and enabling both more accurate and earlier disease detection. However, the relationship between pre-training strategies and downstream performance…

Sustainable artificial intelligence focuses on data, hardware, and algorithms to make machine learning models more environmentally responsible. In particular, machine learning models for speech representations are computationally expensive,…

The marmoset, a highly vocal primate, is a key model for studying social-communicative behavior. Unlike human speech, marmoset vocalizations are less structured, highly variable, and recorded in noisy, low-resource conditions. Learning…

Self-supervised audio representation learning offers an attractive alternative for obtaining generic audio embeddings, capable to be employed into various downstream tasks. Published approaches that consider both audio and words/tags…

Pre-trained vision-language models provide a robust foundation for efficient transfer learning across various downstream tasks. In the field of video action recognition, mainstream approaches often introduce additional modules to capture…

Automatic music transcription (AMT) has achieved high accuracy for piano due to the availability of large, high-quality datasets such as MAESTRO and MAPS, but comparable datasets are not yet available for other instruments. In recent work,…

Arguably one of the top success stories of deep learning is transfer learning. The finding that pre-training a network on a rich source set (eg., ImageNet) can help boost performance once fine-tuned on a usually much smaller target set, has…

In industrial applications, the early detection of malfunctioning factory machinery is crucial. In this paper, we consider acoustic malfunction detection via transfer learning. Contrary to the majority of current approaches which are based…

This paper studies the fast adaptive beamforming for the multiuser multiple-input single-output downlink. Existing deep learning-based approaches assume that training and testing channels follow the same distribution which causes task…

Transformers, which were originally developed for natural language processing, have recently generated significant interest in the computer vision and audio communities due to their flexibility in learning long-range relationships.…

The careful construction of audio representations has become a dominant feature in the design of approaches to many speech tasks. Increasingly, such approaches have emphasized "disentanglement", where a representation contains only parts of…

Transformers serve as the foundational architecture for large language and video generation models, such as GPT, BERT, SORA and their successors. Empirical studies have demonstrated that real-world data and learning tasks exhibit…

In recent years, rapid progress has been made on the problem of single-channel sound separation using supervised training of deep neural networks. In such supervised approaches, a model is trained to predict the component sources from…

Existing dialogue datasets contain lots of noise in their state annotations. Such noise can hurt model training and ultimately lead to poor generalization performance. A general framework named ASSIST has recently been proposed to train…

Unsupervised meta-learning aims to learn feature representations from unsupervised datasets that can transfer to downstream tasks with limited labeled data. In this paper, we propose a novel approach to unsupervised meta-learning that…