Code & Demos

ChiReSSD featured image

ChiReSSD

Speaker-preserving reconstruction of disordered child speech, built on StyleTTS2. Synthesizes a target transcript with canonical pronunciation in the child's own voice.

Read more
MMDyS featured image

MMDyS

Multimodal dysarthria severity assessment that aligns speech, text and facial asymmetry. Includes pretrained video, audio-text and fusion checkpoints.

Read more
Anonymizing Faces, Preserving Anomalies featured image
Cleft Lip

Anonymizing Faces, Preserving Anomalies

Privacy protection for clinical photos of patients with cleft lip. A diffusion model synthesizes a new face around the patient's preserved orofacial region.

Read more
Lip Abnormality Detection for CLP featured image

Lip Abnormality Detection for CLP

Lip normalization and Siamese abnormality detection for patients with repaired cleft lip and palate, trained without patient data.

Read more
G-SELD featured image

G-SELD

Sound event localization and detection in spatial audio with bio-inspired gammatone filters and temporal convolutional networks.

Read more