The field of speech processing has undergone a transformative shift with the advent of deep
learning. The use of multiple processing layers has enabled the creation of models capable …

Neurodevelopmental Disorders (NDD) are a group of conditions with onset in the
developmental period characterized by deficits in the cognitive and social areas …

Large Language Models (LLMs) have demonstrated remarkable capabilities in important
tasks such as natural language understanding and language generation, and thus have the …

Scaling sequence length has become a critical demand in the era of large language models.
However, existing methods struggle with either computational complexity or model …

Transfer learning has recently become the dominant paradigm of machine learning. Pre-
trained models fine-tuned for downstream tasks achieve better performance with fewer …

We present NusaCrowd, a collaborative initiative to collect and unify existing resources for
Indonesian languages, including opening access to previously non-public resources …

Generating speech-consistent body and gesture movements is a long-standing problem in
virtual avatar creation. Previous studies often synthesize pose movement in a holistic …

Automatic speech recognition (ASR) has recently become an important challenge when
using deep learning (DL). It requires large-scale training datasets and high computational …

The remarkable success of transformers in the field of natural language processing has
sparked the interest of the speech-processing community, leading to an exploration of their …

Co-speech gesture is crucial for human-machine interaction and digital entertainment. While
previous works mostly map speech audio to human skeletons (eg, 2D keypoints), directly …