Related papers: Contrastive Learning With Audio Discrimination For…

We study the collaborative image retrieval problem at the wireless edge, where multiple edge devices capture images of the same object, which are then used jointly to retrieve similar images at the edge server over a shared multiple access…

Keyword spotting (KWS) identifies words for voice assistants, but environmental noise frequently reduces accuracy. Standard adaptation fixes this issue and strictly requires original or labeled audio. Test time adaptation (TTA) solves this…

Contrastive learning (CL) continuously achieves significant breakthroughs across multiple domains. However, the most common InfoNCE-based methods suffer from some dilemmas, such as \textit{uniformity-tolerance dilemma} (UTD) and…

The emergence of new spoofing attacks poses an increasing challenge to audio security. Current detection methods often falter when faced with unseen spoofing attacks. Traditional strategies, such as retraining with new data, are not always…

Concurrent Speaker Detection (CSD), the task of identifying active speakers and their overlaps in an audio signal, is essential for various audio applications, including meeting transcription, speaker diarization, and speech separation.…

Contrastive learning has significantly improved representation quality, enhancing knowledge transfer across tasks in continual learning (CL). However, catastrophic forgetting remains a key challenge, as contrastive based methods primarily…

State-of-the-art model for zero-shot cross-lingual spoken language understanding performs cross-lingual unsupervised contrastive learning to achieve the label-agnostic semantic alignment between each utterance and its code-switched data.…

For text enrollment-based open-vocabulary keyword spotting (KWS), acoustic and text embeddings are typically compared at either the phoneme or utterance level. To facilitate this, we optimize acoustic and text encoders using deep metric…

Contrastive learning (CL) has recently emerged as an effective approach to learning representation in a range of downstream tasks. Central to this approach is the selection of positive (similar) and negative (dissimilar) sets to provide the…

Contrastive language-audio pre-training (CLAP) enables zero-shot (ZS) inference of audio and exhibits promising performance in several classification tasks. However, conventional audio representations are still crucial for many tasks where…

Keyword Spotting (KWS) models are becoming increasingly integrated into various systems, e.g. voice assistants. To achieve satisfactory performance, these models typically rely on a large amount of labelled data, limiting their applications…

Continual learning (CL) involves acquiring and accumulating knowledge from evolving tasks while alleviating catastrophic forgetting. Recently, leveraging contrastive loss to construct more transferable and less forgetful representations has…

Universal sound separation (USS) aims to extract arbitrary types of sounds from real-world recordings. This can be achieved by language-queried target sound extraction (TSE), which typically consists of two components: a query network that…

Contrastive learning (CL) has been successful as a powerful representation learning method. In this work we propose CLIM: Contrastive Learning with mutual Information Maximization, to explore the potential of CL on cross-domain sentiment…

Vision-language representation learning largely benefits from image-text alignment through contrastive losses (e.g., InfoNCE loss). The success of this alignment strategy is attributed to its capability in maximizing the mutual information…

Mainstream Audio Analytics models are trained to learn under the paradigm of one class label to many recordings focusing on one task. Learning under such restricted supervision limits the flexibility of models because they require labeled…

Large audio-language models (LALMs) generalize across speech, sound, and music, but unified decoders can exhibit a \emph{temporal smoothing bias}: transient acoustic cues may be underutilized in favor of temporally smooth context that is…

Trigger-word detection plays an important role as the entry point of user's communication with voice assistants. But supporting a particular word as a trigger-word involves huge amount of data collection, augmentation and labelling for that…

Prompt learning has emerged as an efficient and effective method for fine-tuning vision-language models such as CLIP. While many studies have explored generalisation abilities of these models in few-shot classification tasks and a few…

Significant progress has been made in spoken question answering (SQA) in recent years. However, many existing methods, including large audio language models, struggle with processing long audio. Follow the success of retrieval augmented…