相关论文: Language-Based Audio Retrieval with Converging Tie…

The heightened realism of AI-generated images can be attributed to the rapid development of synthetic models, including generative adversarial networks (GANs) and diffusion models (DMs). The malevolent use of synthetic images, such as the…

A study is presented in which a contrastive learning approach is used to extract low-dimensional representations of the acoustic environment from single-channel, reverberant speech signals. Convolution of room impulse responses (RIRs) with…

The performance of voice-controlled systems is usually influenced by accented speech. To make these systems more robust, the frontend accent recognition (AR) technologies have received increased attention in recent years. As accent is a…

The more new features that are being added to smartphones, the harder it becomes for users to find them. This is because the feature names are usually short, and there are just too many to remember. In such a case, the users may want to ask…

Dense retrieval is a basic building block of information retrieval applications. One of the main challenges of dense retrieval in real-world settings is the handling of queries containing misspelled words. A popular approach for handling…

Multi-modal contrastive learning techniques in the audio-text domain have quickly become a highly active area of research. Most works are evaluated with standard audio retrieval and classification benchmarks assuming that (i) these models…

The Contrastive Language-Audio Pretraining (CLAP) model has demonstrated excellent performance in general audio description-related tasks, such as audio retrieval. However, in the emerging field of emotional speaking style description…

Recently, contrastive learning has been shown to be effective in improving pre-trained language models (PLM) to derive high-quality sentence representations. It aims to pull close positive examples to enhance the alignment while push apart…

Dual-encoder-based audio retrieval systems are commonly optimized with contrastive learning on a set of matching and mismatching audio-caption pairs. This leads to a shared embedding space in which corresponding items from the two…

This technical report describes two methods that were developed for Task 2 of the DCASE 2020 challenge. The challenge involves an unsupervised learning to detect anomalous sounds, thus only normal machine working condition samples are…

Embedding-based retrieval models have made significant strides in retrieval-augmented generation (RAG) techniques for text and multimodal large language models (LLMs) applications. However, when it comes to speech larage language models…

Recently, speech separation (SS) task has achieved remarkable progress driven by deep learning technique. However, it is still challenging to separate target speech from noisy mixture, as the neural model is vulnerable to assign background…

We propose a framework using contrastive learning as a pre-training task to perform image classification in the presence of noisy labels. Recent strategies such as pseudo-labeling, sample selection with Gaussian Mixture models, weighted…

Accent variability has posed a huge challenge to automatic speech recognition~(ASR) modeling. Although one-hot accent vector based adaptation systems are commonly used, they require prior knowledge about the target accent and cannot handle…

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…

The innate correlation between a person's face and voice has recently emerged as a compelling area of study, especially within the context of multilingual environments. This paper introduces our novel solution to the Face-Voice Association…

Machine hearing of the environmental sound is one of the important issues in the audio recognition domain. It gives the machine the ability to discriminate between the different input sounds that guides its decision making. In this work we…

Weak-to-strong generalization provides a promising paradigm for scaling large language models (LLMs) by training stronger models on samples from aligned weaker ones, without requiring human feedback or explicit reward modeling. However, its…

Contrastive learning has been widely used to train transformer-based vision-language models for video-text alignment and multi-modal representation learning. This paper presents a new algorithm called Token-Aware Cascade contrastive…

Packet loss concealment (PLC) is challenging in concealing missing contents both plausibly and naturally when there are only limited available context to use. Recently deep-learning based PLC algorithms have demonstrated their superiority…