Deaf learners in the Global South struggle to access equitable education, in particular, there
are few instances where they can be facilitated in inclusive classrooms. The challenges …

This paper presents the development of a speech synthesis system for the LIMMITS'24
Challenge, focusing primarily on Track 2. The objective of the challenge is to establish a …

Although current fake audio detection approaches have achieved remarkable success on
specific datasets, they often fail when evaluated with datasets from different distributions …

The generalization of Fake Audio Detection (FAD) is critical due to the emergence of new
spoofing techniques. Traditional FAD methods often focus solely on distinguishing between …

Text-to-Audio (TTA) aims to generate audio that corresponds to the given text description,
playing a crucial role in media production. The text descriptions in TTA datasets lack rich …

In the field of deepfake detection, previous studies focus on using reconstruction or mask
and prediction methods to train pre-trained models, which are then transferred to fake audio …

Most of current end-to-end speech synthesis assumes the input text is in a single language
situation. However, codeswitching in speech occurs frequently in routine life, in which …

End-to-end framework can generate high-quality and high-similarity speech in the
personalized speech synthesis task. However, the generalization of out-of-domain texts is …

This paper presents current work being done on the development of a speech and language
technology (SLT) based intelligent tutoring system for coaching young learners from a …

Artificial speech has been present in our lives in several aspects. From automatic messages
when you didn't answer your phone years ago to movies that portray robots capable of …