Related papers: Consistent and Relevant: Rethink the Query Embeddi…
Deep learning-based language models have achieved state-of-the-art results in a number of applications including sentiment analysis, topic labelling, intent classification and others. Obtaining text representations or embeddings using these…
Feature mapping using deep neural networks is an effective approach for single-channel speech enhancement. Noisy features are transformed to the enhanced ones through a mapping network and the mean square errors between the enhanced and…
Confusing classes that are ubiquitous in real world often degrade performance for many vision related applications like object detection, classification, and segmentation. The confusion errors are not only caused by similar visual patterns…
The objective of deep learning methods based on encoder-decoder architectures for music source separation is to approximate either ideal time-frequency masks or spectral representations of the target music source(s). The spectral…
Source separation is a crucial pre-processing step for various speech processing tasks, such as automatic speech recognition (ASR). Traditionally, the evaluation metrics for speech separation rely on the matched reference audios and…
Music source separation has been a popular topic in signal processing for decades, not only because of its technical difficulty, but also due to its importance to many commercial applications, such as automatic karoake and remixing. In this…
Generative models have attracted considerable attention for speech separation tasks, and among these, diffusion-based methods are being explored. Despite the notable success of diffusion techniques in generation tasks, their adaptation to…
The rapid expansion of remote sensing image archives demands the development of strong and efficient techniques for content-based image retrieval (RS-CBIR). This paper presents REJEPA (Retrieval with Joint-Embedding Predictive…
We consider the problem of finding equivalent minimal-size reformulations of SQL queries in presence of embedded dependencies [1]. Our focus is on select-project-join (SPJ) queries with equality comparisons, also known as safe conjunctive…
Lifelong user behavior sequences are crucial for capturing user interests and predicting user responses in modern recommendation systems. A two-stage paradigm is typically adopted to handle these long sequences: a subset of relevant…
Target speaker extraction (TSE) is a technique for isolating a target speaker's voice from mixed speech using auxiliary features associated with the target speaker. It is another attempt at addressing the cocktail party problem and is…
Extracting individual elements from music mixtures is a valuable tool for music production and practice. While neural networks optimized to mask or transform mixture spectrograms into the individual source(s) have been the leading approach,…
Recent progress in audio source separation lead by deep learning has enabled many neural network models to provide robust solutions to this fundamental estimation problem. In this study, we provide a family of efficient neural network…
Distributed microphone array (DMA) is a promising next-generation platform for speech interaction, where speech enhancement (SE) is still required to improve the speech quality in noisy cases. Existing SE methods usually first gather raw…
The efficacy of self-supervised speech models has been validated, yet the optimal utilization of their representations remains challenging across diverse tasks. In this study, we delve into Acoustic Word Embeddings (AWEs), a fixed-length…
This paper presents a joint source separation algorithm that simultaneously reduces acoustic echo, reverberation and interfering sources. Target speeches are separated from the mixture by maximizing independence with respect to the other…
Recent studies have been revisiting whole words as the basic modelling unit in speech recognition and query applications, instead of phonetic units. Such whole-word segmental systems rely on a function that maps a variable-length speech…
Audio DeepFakes are utterances generated with the use of deep neural networks. They are highly misleading and pose a threat due to use in fake news, impersonation, or extortion. In this work, we focus on increasing accessibility to the…
Zero-shot speaker adaptation aims to clone an unseen speaker's voice without any adaptation time and parameters. Previous researches usually use a speaker encoder to extract a global fixed speaker embedding from reference speech, and…
Semantic caching enhances the efficiency of large language model (LLM) systems by identifying semantically similar queries, storing responses once, and serving them for subsequent equivalent requests. However, existing semantic caching…