Related papers: SPICE: Self-supervised Pitch Estimation

In the domain of music and sound processing, pitch extraction plays a pivotal role. Our research presents a specialized convolutional neural network designed for pitch extraction, particularly from the human singing voice in acapella…

In the context of environmental sound classification, the adaptability of systems is key: which sound classes are interesting depends on the context and the user's needs. Recent advances in text-to-audio retrieval allow for zero-shot audio…

An event camera is a novel vision sensor that can capture per-pixel brightness changes and output a stream of asynchronous ``events''. It has advantages over conventional cameras in those scenes with high-speed motions and challenging…

Convolutional Neural Networks (CNNs) need large amounts of data with ground truth annotation, which is a challenging problem that has limited the development and fast deployment of CNNs for many computer vision tasks. We propose a novel…

At present, deep learning has been applied more and more in monocular image depth estimation and has shown promising results. The current more ideal method for monocular depth estimation is the supervised learning based on ground truth…

Acoustic word embeddings (AWEs) aims to map a variable-length speech segment into a fixed-dimensional representation. High-quality AWEs should be invariant to variations, such as duration, pitch and speaker. In this paper, we introduce a…

Self-supervised monocular depth estimation holds significant importance in the fields of autonomous driving and robotics. However, existing methods are typically trained and tested on standard datasets, overlooking the impact of various…

Despite recent achievements of deep learning automatic music generation algorithms, few approaches have been proposed to evaluate whether a single-track music excerpt is composed by automatons or Homo sapiens. To tackle this problem, we…

In the broadcast domain there is an abundance of related text data and partial transcriptions, such as closed captions and subtitles. This text data can be used for lightly supervised training, in which text matching the audio is selected…

This paper introduces a novel method to separate noisy speech into low or high frequency frames, in order to improve fundamental frequency (F0) estimation accuracy. In this proposal, the target signal is analyzed by means of the ensemble…

Monocular depth inference has gained tremendous attention from researchers in recent years and remains as a promising replacement for expensive time-of-flight sensors, but issues with scale acquisition and implementation overhead still…

Time delay estimation or Time-Difference-Of-Arrival estimates is a critical component for multiple localization applications such as multilateration, direction of arrival, and self-calibration. The task is to estimate the time difference…

We investigated, by using auditory models, how three perceptual parameters, loudness, pitch and sharpness, determine human echolocation. We used acoustic recordings from two previous studies, both from stationary situations, and their…

This paper presents one-bit supervision, a novel setting of learning from incomplete annotations, in the scenario of image classification. Instead of training a model upon the accurate label of each sample, our setting requires the model to…

Self-supervised learning can significantly improve the performance of downstream tasks, however, the dimensions of learned representations normally lack explicit physical meanings. In this work, we propose a novel self-supervised approach…

Human perception has the unique ability to focus on specific events in a mixture of signals--a challenging task for existing non-intrusive assessment methods. In this work, we introduce semi-intrusive assessment that emulates human…

Sounds reach one microphone in a stereo pair sooner than the other, resulting in an interaural time delay that conveys their directions. Estimating a sound's time delay requires finding correspondences between the signals recorded by each…

Self-supervised monocular depth estimation networks are trained to predict scene depth using nearby frames as a supervision signal during training. However, for many applications, sequence information in the form of video frames is also…

The quantum phase estimation (QPE) is one of the fundamental algorithms based on the quantum Fourier transform. It has applications in order-finding, factoring, and finding the eigenvalues of unitary operators. The major challenge in…

Isolating the voice of a specific person while filtering out other voices or background noises is challenging when video is shot in noisy environments. We propose audio-visual methods to isolate the voice of a single speaker and eliminate…