Related papers: MBI-Net: A Non-Intrusive Multi-Branched Speech Int…

Large-scale sound recognition data sets typically consist of acoustic recordings obtained from multimedia libraries. As a consequence, modalities other than audio can often be exploited to improve the outputs of models designed for…

Speech enhancement (SE) is critical for improving speech intelligibility and quality in real-world environments, particularly for cochlear implant (CI) users who experience severe degradations in speech understanding under noisy and…

This paper presents a review of multi-objective deep learning methods that have been introduced in the literature for speech denoising. After stating an overview of conventional, single objective deep learning, and hybrid or combined…

We propose an end-to-end joint optimization framework of a multi-channel neural speech extraction and deep acoustic model without mel-filterbank (FBANK) extraction for overlapped speech recognition. First, based on a multi-channel…

Most deep learning-based models for speech enhancement have mainly focused on estimating the magnitude of spectrogram while reusing the phase from noisy speech for reconstruction. This is due to the difficulty of estimating the phase of…

Human decision-making in high-stakes domains often relies on expertise and heuristics, but is vulnerable to hard-to-detect cognitive biases that threaten fairness and long-term outcomes. This work presents a novel approach to enhancing…

Silent speech interface (SSI) enables hands-free input without audible vocalization, but most SSI systems do not verify speaker identity. We present HEar-ID, which uses consumer active noise-canceling earbuds to capture low-frequency…

In this paper, a novel architecture for speaker recognition is proposed by cascading speech enhancement and speaker processing. Its aim is to improve speaker recognition performance when speech signals are corrupted by noise. Instead of…

Around 466 million people worldwide (over 5% of the world's population) have disabling hearing loss, and out of these 34 million are children. Estimates suggest that by 2050, over 900 million people worldwide will have disabling hearing…

Respiratory diseases remain major global health challenges, and traditional auscultation is often limited by subjectivity, environmental noise, and inter-clinician variability. This study presents an explainable multimodal deep learning…

The objective speech quality assessment is usually conducted by comparing received speech signal with its clean reference, while human beings are capable of evaluating the speech quality without any reference, such as in the mean opinion…

In crowded settings, the human brain can focus on speech from a target speaker, given prior knowledge of how they sound. We introduce a novel intelligent hearable system that achieves this capability, enabling target speech hearing to…

While traditional statistical signal processing model-based methods can derive the optimal estimators relying on specific statistical assumptions, current learning-based methods further promote the performance upper bound via deep neural…

Hate speech detection has become an important research topic within the past decade. More private corporations are needing to regulate user generated content on different platforms across the globe. In this paper, we introduce a study of…

Estimation of a speaker's direction and head orientation with binaural recordings can be a critical piece of information in many real-world applications with emerging `earable' devices, including smart headphones and AR/VR headsets.…

Hierarchical models are utilized in a wide variety of problems which are characterized by task hierarchies, where predictions on smaller subtasks are useful for trying to predict a final task. Typically, neural networks are first trained…

Modern noise-cancelling headphones have significantly improved users' auditory experiences by removing unwanted background noise, but they can also block out sounds that matter to users. Machine learning (ML) models for sound event…

Understanding degraded speech is demanding, requiring increased listening effort (LE). Evaluating processed and unprocessed speech with respect to LE can objectively indicate if speech enhancement systems benefit listeners. However,…

Dementia is a syndrome, generally of a chronic nature characterized by a deterioration in cognitive function, especially in the geriatric population and is severe enough to impact their daily activities. Early diagnosis of dementia is…

Speech enhancement aims to improve speech quality and intelligibility in noisy environments. Recent advancements have concentrated on deep neural networks, particularly employing the Two-Stage (TS) architecture to enhance feature…