Papers by Carla Viegas
Entheos: A Multimodal Dataset for Studying Enthusiasm (2021.findings-acl)
Copied to clipboard
| Challenge: | Enthusiasm is an important part of engaging communication. |
| Approach: | They propose a multimodal dataset for studying enthusiasm composed of video, audio, and text. |
| Outcome: | The proposed model shows that pitch, loudness, and discourse relation parsing are important in distinguishing enthusiastic communication. |
Including Facial Expressions in Contextual Embeddings for Sign Language Generation (2023.starsem-1)
Copied to clipboard
| Challenge: | State-of-the-art sign language generation frameworks lack expressivity and naturalness . current systems focus on manual signs, neglecting affective, grammatical and semantic functions of facial expressions . communication between the Deaf and Hard of Hearing (DHH) individuals may be facilitated by emerging language technologies . |
| Approach: | They propose a Dual Encoder Transformer capable of generating manual signs and facial expressions by capturing similarities and differences found in text and sign gloss annotations. |
| Outcome: | The proposed model improves the quality of automatically generated sign language. |