Related papers: Investigating Cross-Domain Losses for Speech Enhan…
Target speaker extraction (TSE) aims to isolate a specific speaker's voice from multi-speaker mixtures. Despite strong benchmark results, real-world performance often degrades due to different interacting factors. Previous curriculum…
Emotion recognition from speech is one of the key steps towards emotional intelligence in advanced human-machine interaction. Identifying emotions in human speech requires learning features that are robust and discriminative across diverse…
Existing deep learning (DL) based speech enhancement approaches are generally optimised to minimise the distance between clean and enhanced speech features. These often result in improved speech quality however they suffer from a lack of…
Self-supervised learning (SSL) leverages large datasets of unlabeled speech to reach impressive performance with reduced amounts of annotated data. The high number of proposed approaches fostered the emergence of comprehensive benchmarks…
Diffusion model, as a new generative model which is very popular in image generation and audio synthesis, is rarely used in speech enhancement. In this paper, we use the diffusion model as a module for stochastic refinement. We propose…
Performance in Speech Emotion Recognition (SER) on a single language has increased greatly in the last few years thanks to the use of deep learning techniques. However, cross-lingual SER remains a challenge in real-world applications due to…
The time domain waveform of a speech signal carries all of the auditory information. From the phonological point of view, it little can be said on the basis of the waveform itself. However, past research in mathematics, acoustics, and…
Self-supervised learning enables the training of large neural models without the need for large, labeled datasets. It has been generating breakthroughs in several fields, including computer vision, natural language processing, biology, and…
Speech enhancement(SE) aims to recover clean speech from noisy recordings. Although generative approaches such as score matching and Schrodinger bridge have shown strong effectiveness, they are often computationally expensive. Flow matching…
Partial audio deepfake localization poses unique challenges and remain underexplored compared to full-utterance spoofing detection. While recent methods report strong in-domain performance, their real-world utility remains unclear. In this…
Multi-channel acoustic signal processing is a well-established and powerful tool to exploit the spatial diversity between a target signal and non-target or noise sources for signal enhancement. However, the textbook solutions for optimal…
In this paper, a novel architecture for speaker recognition is proposed by cascading speech enhancement and speaker processing. Its aim is to improve speaker recognition performance when speech signals are corrupted by noise. Instead of…
Speech enhancement is widely used as a front-end to improve the speech quality in many audio systems, while it is hard to extract the target speech in multi-talker conditions without prior information on the speaker identity. It was shown…
This paper presents a novel discriminator-constrained optimal transport network (DOTN) that performs unsupervised domain adaptation for speech enhancement (SE), which is an essential regression task in speech processing. The DOTN aims to…
Generative adversarial network-based models have shown remarkable performance in the field of speech enhancement. However, the current optimization strategies for these models predominantly focus on refining the architecture of the…
In recent years, speech processing algorithms have seen tremendous progress primarily due to the deep learning renaissance. This is especially true for speech separation where the time-domain audio separation network (TasNet) has led to…
This thesis focuses on representation learning for sequence data over time or space, aiming to improve downstream sequence prediction tasks by using the learned representations. Supervised learning has been the most dominant approach for…
Despite speaker verification has achieved significant performance improvement with the development of deep neural networks, domain mismatch is still a challenging problem in this field. In this study, we propose a novel framework to…
Spectral subtraction, widely used for its simplicity, has been employed to address the Robot Ego Speech Filtering (RESF) problem for detecting speech contents of human interruption from robot's single-channel microphone recordings when it…
Speaker verification, as a biometric authentication mechanism, has been widely used due to the pervasiveness of voice control on smart devices. However, the task of "in-the-wild" speaker verification is still challenging, considering the…