相关论文: Nosey: Open-source hardware for acoustic nasalance

Breath with nose sound features has been shown as a potential biometric in personal identification and verification. In this paper, we show that information that comes from other modalities captured by motion sensors on the chest in…

Background noise is a major source of quality impairments in Voice over Internet Protocol (VoIP) and Public Switched Telephone Network (PSTN) calls. Recent work shows the efficacy of deep learning for noise suppression, but the datasets…

Estimation of perceptual quality in audio and speech is possible using a variety of methods. The combined v3 release of ViSQOL and ViSQOLAudio (for speech and audio, respectively,) provides improvements upon previous versions, in terms of…

Natural language interfaces (NLIs) have become a prevalent medium for conducting visual data analysis, enabling people with varying levels of analytic experience to ask questions of and interact with their data. While there have been…

We present the DIScrete PERsistent Structures Extractor (DisPerSE), an open source software for the automatic and robust identification of structures in 2D and 3D noisy data sets. The software is designed to identify all sorts of…

In noisy environments, speech can be hard to understand for humans. Spoken dialog systems can help to enhance the intelligibility of their output, either by modifying the speech synthesis (e.g., imitate Lombard speech) or by optimizing the…

Systematic evaluation of speech separation and enhancement models under moving sound source conditions requires extensive and diverse data. However, real-world datasets often lack sufficient data for training and evaluation, and synthetic…

We present a novel multi-modal unspoken punctuation prediction system for the English language which combines acoustic and text features. We demonstrate for the first time, that by relying exclusively on synthetic data generated using a…

We present an easily reproducible, open-source, sound card based experimental set-up to support transfer function measurement. Our system is able to visualize signals of mechanical and electrical resonances and their spectra in real time.…

Active Learning (AL) aims to reduce annotation costs by strategically selecting the most informative samples for labeling. However, most active learning methods struggle in the low-budget regime where only a few labeled examples are…

We introduce Seshat, a new, simple and open-source software to efficiently manage annotations of speech corpora. The Seshat software allows users to easily customise and manage annotations of large audio corpora while ensuring compliance…

The paper proposes an efficient, robust, and reconfigurable technique to suppress various types of noises for any sampling rate. The theoretical analyses, subjective and objective test results show that the proposed noise suppression (NS)…

Deploying speech enhancement (SE) systems in wearable devices, such as smart glasses, is challenging due to the limited computational resources on the device. Although deep learning methods have achieved high-quality results, their…

Own voice pickup for hearables in noisy environments benefits from using both an outer and an in-ear microphone outside and inside the occluded ear. Due to environmental noise recorded at both microphones, and amplification of the own voice…

We introduce SoundSpaces 2.0, a platform for on-the-fly geometry-based audio rendering for 3D environments. Given a 3D mesh of a real-world environment, SoundSpaces can generate highly realistic acoustics for arbitrary sounds captured from…

We describe a system for interrogating the acoustic properties of sub-nanoliter liquid samples within an open microfluidics platform. Sessile droplets were deposited onto integrated optomechanical sensors, which possess…

This paper introduces a novel neural network-based speech coding system that can process noisy speech effectively. The proposed source-aware neural audio coding (SANAC) system harmonizes a deep autoencoder-based source separation model and…

For deep learning-based speech enhancement (SE) systems, the training-test acoustic mismatch can cause notable performance degradation. To address the mismatch issue, numerous noise adaptation strategies have been derived. In this paper, we…

Large-scale datasets in the real world inevitably involve label noise. Deep models can gradually overfit noisy labels and thus degrade model generalization. To mitigate the effects of label noise, learning with noisy labels (LNL) methods…

Addressing mixed closed-set and open-set label noise in medical image classification remains a largely unexplored challenge. Unlike natural image classification, which often separates and processes closed-set and open-set noisy samples from…