Related papers: STRAUSS: Sonification Tools & Resources for Analys…
Training personalized speech enhancement models is innately a no-shot learning problem due to privacy constraints and limited access to noise-free speech from the target user. If there is an abundance of unlabeled noisy speech from the…
The large size of nowadays' online multimedia databases makes retrieving their content a difficult and time-consuming task. Users of online sound collections typically submit search queries that express a broad intent, often making the…
The visualization of publication and citation data is popular in bibliometrics. Although less common, the representation of empirical data as sound is an alternative form of presentation (in other fields than bibliometrics). In this…
Humans are able to localize objects in the environment using both visual and auditory cues, integrating information from multiple modalities into a common reference frame. We introduce a system that can leverage unlabeled audio-visual data…
Materials science literature contains millions of materials synthesis procedures described in unstructured natural language text. Large-scale analysis of these synthesis procedures would facilitate deeper scientific understanding of…
We demonstrate tools and applications developed based on the method of "sound safeguarding," which enables any sound to be used for acoustic measurements. We developed tools for preparation, interactive and real-time measurement, and report…
Context: Data from ground-based, high-resolution solar telescopes can only be used for science with calibrations and processing, which requires detailed knowledge about the instrumentation. [...] Aims: We aim to provide observers with a…
This work proposes a learning-based statistical refinement method for improving the denoising results of a given denoiser without knowing the precise noise distribution or accessing clean images or calibration data. While there are many…
3D object detection aims to recover the 3D information of concerning objects and serves as the fundamental task of autonomous driving perception. Its performance greatly depends on the scale of labeled training data, yet it is costly to…
Speaker diarization has gained considerable attention within speech processing research community. Mainstream speaker diarization rely primarily on speakers' voice characteristics extracted from acoustic signals and often overlook the…
Existing topic modeling and text segmentation methodologies generally require large datasets for training, limiting their capabilities when only small collections of text are available. In this work, we reexamine the inter-related problems…
Automatic Speech Understanding (ASU) leverages the power of deep learning models for accurate interpretation of human speech, leading to a wide range of speech applications that enrich the human experience. However, training a robust ASU…
Collecting accurate and fine-grain information about the music people like, dislike and actually listen to has long been a challenge for sociologists. As millions of people now use online music streaming services, research can build upon…
We present Synthio, a novel approach for augmenting small-scale audio classification datasets with synthetic data. Our goal is to improve audio classification accuracy with limited labeled data. Traditional data augmentation techniques,…
Most of the solar physicists use very expensive software for data reduction and visualization. We present hereafter a reliable freeware solution based on the Python language. This is made possible by the association of the latter with a…
This paper describes an object-oriented approach to music composition and sound design. The approach unifies the processes of music making and instrument building by using similar logic, objects, and procedures. The composition modules use…
How to visually localize multiple sound sources in unconstrained videos is a formidable problem, especially when lack of the pairwise sound-object annotations. To solve this problem, we develop a two-stage audiovisual learning framework…
Cinematic Audio Source Separation (CASS) aims to decompose mixed film audio into speech, music, and sound effects, enabling applications like dubbing and remastering. Existing CASS approaches are audio-only, overlooking the inherent…
Accurate and efficient simulation of room impulse responses is crucial for spatial audio applications. However, existing acoustic ray-tracing tools often operate as black boxes and only output impulse responses (IRs), providing limited…
This paper presents Praaline, an open-source software system for managing, annotating, analysing and visualising speech corpora. Researchers working with speech corpora are often faced with multiple tools and formats, and they need to work…