Related papers: Enhancing Self-Supervised Talking Head Forgery Det…

In this paper, we present a framework for contrastive learning for audio representations, in a self supervised frame work without access to any ground truth labels. The core idea in self supervised contrastive learning is to map an audio…

Recently, fault diagnosis methods for marine machinery systems based on deep learning models have attracted considerable attention in the shipping industry. Most existing studies assume fault classes are consistent and known between the…

We introduce a data-driven anomaly detection framework using a manufacturing dataset collected from a factory assembly line. Given heterogeneous time series data consisting of operation cycle signals and sensor signals, we aim at…

Transformer-based models have shown strong performance in speech deepfake detection, largely due to the effectiveness of the multi-head self-attention (MHSA) mechanism. MHSA provides frame-level attention scores, which are particularly…

Speech production is a complex phenomenon, wherein the brain orchestrates a sequence of processes involving thought processing, motor planning, and the execution of articulatory movements. However, this intricate execution of various…

Modern automatic speech recognition (ASR) systems have been observed to function better for certain speaker groups (SGs) than others, despite recent gains in overall performance. One potential impediment to progress towards fairer ASR is a…

Recent years have witnessed wider adoption of Automated Speech Recognition (ASR) techniques in various domains. Consequently, evaluating and enhancing the quality of ASR systems is of great importance. This paper proposes ASDF, an Automated…

Generative speech enhancement (GSE) models show great promise in producing high-quality clean speech from noisy inputs, enabling applications such as curating noisy text-to-speech (TTS) datasets into high-quality ones. However, GSE models…

Self-supervised learning (SSL) has been investigated to generate task-agnostic representations across various domains. However, such investigation has not been conducted for detecting multiple mental disorders. The rationale behind the…

When the available data of a target speaker is insufficient to train a high quality speaker-dependent neural text-to-speech (TTS) system, we can combine data from multiple speakers and train a multi-speaker TTS model instead. Many studies…

Masked Diffusion Models (MDMs) offer a promising alternative to autoregressive language models by enabling parallel token generation and bidirectional context modeling. However, their inference speed is significantly limited by the…

As a kind of generative self-supervised learning methods, generative adversarial nets have been widely studied in the field of anomaly detection. However, the representation learning ability of the generator is limited since it pays too…

Existing methods for deepfake audio detection have demonstrated some effectiveness. However, they still face challenges in generalizing to new forgery techniques and evolving attack patterns. This limitation mainly arises because the models…

The existing fake audio detection systems often rely on expert experience to design the acoustic features or manually design the hyperparameters of the network structure. However, artificial adjustment of the parameters can have a…

We consider the problem of training speech recognition systems without using any labeled data, under the assumption that the learner can only access to the input utterances and a phoneme language model estimated from a non-overlapping…

The label-embedded dictionary learning (DL) algorithms generate influential dictionaries by introducing discriminative information. However, there exists a limitation: All the label-embedded DL methods rely on the labels due that this way…

In ML-aided decision-making tasks, such as fraud detection or medical diagnosis, the human-in-the-loop, usually a domain-expert without technical ML knowledge, prefers high-level concept-based explanations instead of low-level explanations…

We propose the application of a semi-supervised learning method to improve the performance of acoustic modelling for automatic speech recognition based on deep neural net- works. As opposed to unsupervised initialisation followed by…

Semi-supervised learning is the problem of training an accurate predictive model by combining a small labeled dataset with a presumably much larger unlabeled dataset. Many methods for semi-supervised deep learning have been developed,…

Machine learning is making substantial progress in diverse applications. The success is mostly due to advances in deep learning. However, deep learning can make mistakes and its generalization abilities to new tasks are questionable. We ask…