Xugang Lu

Speech Behavior Analysis by Articulatory Observations

2017 · Procedia Computer Science

In articulatory phonetics, the place and manner of articulation indicate setting and action of the articulators during production of speech sounds. The place and manner are varied in pronouncing phonetic components such as vowel, bilabial, …

Relationship Between Speakers' Physiological Structure and Acoustic Speech Signals: Data-Driven Study Based on Frequency-Wise Attentional Neural Network

2022 · 2022 30th European Signal Processing Conference (EUSIPCO)

Quantitatively revealing the relationship between speakers' physiological structure and acoustic speech signals by considering the properties of resonance and antiresonance can help us to extract effective speaker discriminative information (SDI) from speech signals. The conventional …

Hierarchical Cross-Modality Knowledge Transfer with Sinkhorn Attention for CTC-based ASR

2023 · arXiv (Cornell University)

Due to the modality discrepancy between textual and acoustic modeling, efficiently transferring linguistic knowledge from a pretrained language model (PLM) to acoustic encoding for automatic speech recognition (ASR) still remains a challenging task. In this …