相关论文: Towards Learning Universal Audio Representations

Since the advent of Deep Learning (DL), Speech Enhancement (SE) models have performed well under a variety of noise conditions. However, such systems may still introduce sonic artefacts, sound unnatural, and restrict the ability for a user…

The practical deployment of Audio-Visual Speech Recognition (AVSR) systems is fundamentally challenged by significant performance degradation in real-world environments, characterized by unpredictable acoustic noise and visual interference.…

The detection of acoustic scenes is a challenging problem in which environmental sound events must be detected from a given audio signal. This includes classifying the events as well as estimating their onset and offset times. We approach…

Self-supervised audio representation learning offers an attractive alternative for obtaining generic audio embeddings, capable to be employed into various downstream tasks. Published approaches that consider both audio and words/tags…

Mel-filterbanks are fixed, engineered audio features which emulate human perception and have been used through the history of audio understanding up to today. However, their undeniable qualities are counterbalanced by the fundamental…

Even in the absence of any explicit semantic annotation, vast collections of audio recordings provide valuable information for learning the categorical structure of sounds. We consider several class-agnostic semantic constraints that apply…

This paper provides an overview of recent progress in non-intrusive speech intelligibility prediction for hearing aids (HA). We summarize developments in robust acoustic feature extraction, hearing loss modeling, and the use of emerging…

Benefiting from the development of deep learning, text-to-speech (TTS) techniques using clean speech have achieved significant performance improvements. The data collected from real scenes often contains noise and generally needs to be…

Identifying acoustic events from a continuously streaming audio source is of interest for many applications including environmental monitoring for basic research. In this scenario neither different event classes are known nor what…

According to the Complementary Learning Systems (CLS) theory~\cite{mcclelland1995there} in neuroscience, humans do effective \emph{continual learning} through two complementary systems: a fast learning system centered on the hippocampus for…

Self-supervised learning (SSL) is a long-standing goal for speech processing, since it utilizes large-scale unlabeled data and avoids extensive human labeling. Recent years witness great successes in applying self-supervised learning in…

This paper introduces the Procedural (audio) Variational autoEncoder (ProVE) framework as a general approach to learning Procedural Audio PA models of environmental sounds with an improvement to the realism of the synthesis while…

This technical report describes the systems submitted to the DCASE2022 challenge task 3: sound event localization and detection (SELD). The task aims to detect occurrences of sound events and specify their class, furthermore estimate their…

Transcranial ultrasound therapy is increasingly used for the non-invasive treatment of brain disorders. However, conventional numerical wave solvers are currently too computationally expensive to be used online during treatments to predict…

Audio fingerprinting systems must efficiently and robustly identify query snippets in an extensive database. To this end, state-of-the-art systems use deep learning to generate compact audio fingerprints. These systems deploy indexing…

Sounds are essential to how humans perceive and interact with the world and are captured in recordings and shared on the Internet on a minute-by-minute basis. These recordings, which are predominantly videos, constitute the largest archive…

Research on speech processing has traditionally considered the task of designing hand-engineered acoustic features (feature engineering) as a separate distinct problem from the task of designing efficient machine learning (ML) models to…

This work presents a novel framework based on feed-forward neural network for text-independent speaker classification and verification, two related systems of speaker recognition. With optimized features and model training, it achieves 100%…

It is known that, without awareness of the process, our brain appears to focus on the general shape of objects rather than superficial statistics of context. On the other hand, learning autonomously allows discovering invariant regularities…

The learning of interpretable representations from raw data presents significant challenges for time series data like speech. In this work, we propose a relevance weighting scheme that allows the interpretation of the speech representations…