5 papers
Can Prosodic Style Be Inferred from Text Alone? Evidence from Unsupervised Acoustic Clusters
Abdul Rehman, Jian-Jun Zhang, Xiaosong Yang
Much of expressive text-to-speech research rests on an untested assumption that written text carries enough information to select an appropriate prosodic style for its delivery. Te…
BFA: Real-time Multilingual Text-to-speech Forced Alignment
Abdul Rehman, Jingyao Cai, Jian-Jun Zhang +1
We present Bournemouth Forced Aligner (BFA), a system that combines a Contextless Universal Phoneme Encoder (CUPE) with a connectionist temporal classification (CTC)based decoder.…
CUPE: Contextless Universal Phoneme Encoder for Language-Agnostic Speech Processing
Abdul Rehman, Jian-Jun Zhang, Xiaosong Yang
Universal phoneme recognition typically requires analyzing long speech segments and language-specific patterns. Many speech processing tasks require pure phoneme representations fr…
MaSkel: A Model for Human Whole-body X-rays Generation from Human Masking Images
Yingjie Xi, Boyuan Cheng, Jingyao Cai +2
The human whole-body X-rays could offer a valuable reference for various applications, including medical diagnostics, digital animation modeling, and ergonomic design. The traditio…
CLARA: Multilingual Contrastive Learning for Audio Representation Acquisition
Kari A Noriy, Xiaosong Yang, Marcin Budka +1
Multilingual speech processing requires understanding emotions, a task made difficult by limited labelled data. CLARA, minimizes reliance on labelled data, enhancing generalization…