Related papers: AudioFormer: Audio Transformer learns audio featur…

We investigate the potential of stochastic neural networks for learning effective waveform-based acoustic models. The waveform-based setting, inherent to fully end-to-end speech recognition systems, is motivated by several comparative…

Neural network models using predictive coding are interesting from the viewpoint of computational modelling of human language acquisition, where the objective is to understand how linguistic units could be learned from speech without any…

This paper presents an audio visual automatic speech recognition (AV-ASR) system using a Transformer-based architecture. We particularly focus on the scene context provided by the visual information, to ground the ASR. We extract…

Referring image segmentation aims to segment an object referred to by natural language expression from an image. The primary challenge lies in the efficient propagation of fine-grained semantic information from textual features to visual…

Recent advancements in pattern recognition and signal processing concern the automatic learning of data representations from labeled training samples. Typical approaches are based on deep learning and convolutional neural networks, which…

This work presents a framework based on feature disentanglement to learn speaker embeddings that are robust to environmental variations. Our framework utilises an auto-encoder as a disentangler, dividing the input speaker embedding into…

This paper introduces an unsupervised framework for detecting audio patterns in musical samples (loops) through anomaly detection techniques, addressing challenges in music information retrieval (MIR). Existing methods are often constrained…

We present VoiceRestore, a novel approach to restoring the quality of speech recordings using flow-matching Transformers trained in a self-supervised manner on synthetic data. Our method tackles a wide range of degradations frequently found…

Continuous speech can be converted into a discrete sequence by deriving discrete units from the hidden features of self-supervised learned (SSL) speech models. Although SSL models are becoming larger and trained on more data, they are often…

In anomalous sound detection, the discriminative method has demonstrated superior performance. This approach constructs a discriminative feature space through the classification of the meta-information labels for normal sounds. This feature…

This paper presents a method of sequence-to-sequence (seq2seq) voice conversion using non-parallel training data. In this method, disentangled linguistic and speaker representations are extracted from acoustic features, and voice conversion…

Environmental Sound Classification (ESC) is a challenging field of research in non-speech audio processing. Most of current research in ESC focuses on designing deep models with special architectures tailored for specific audio datasets,…

For centuries researchers have used sound to monitor and study wildlife. Traditionally, conservationists have identified species by ear; however, it is now common to deploy audio recording technology to monitor animal and ecosystem sounds.…

We consider the task of unsupervised extraction of meaningful latent representations of speech by applying autoencoding neural networks to speech waveforms. The goal is to learn a representation able to capture high level semantic content…

In speech processing pipelines, improving the quality and intelligibility of real-world recordings is crucial. While supervised regression is the primary method for speech enhancement, audio tokenization is emerging as a promising…

The difficulty of acquiring abundant, high-quality data, especially in multi-lingual contexts, has sparked interest in addressing low-resource scenarios. Moreover, current literature rely on fixed expressions from language IDs, which…

While deep learning-based models like transformers, have revolutionized time-series and vision tasks, they remain highly susceptible to noise and often overfit on noisy patterns rather than robust features. This issue is exacerbated in…

Contrastive predictive coding (CPC) aims to learn representations of speech by distinguishing future observations from a set of negative examples. Previous work has shown that linear classifiers trained on CPC features can accurately…

Acoustic-to-Word recognition provides a straightforward solution to end-to-end speech recognition without needing external decoding, language model re-scoring or lexicon. While character-based models offer a natural solution to the…

Current generative models are able to generate high-quality artefacts but have been shown to struggle with compositional reasoning, which can be defined as the ability to generate complex structures from simpler elements. In this paper, we…