4 papers
The Role of Vocal Persona in Natural and Synthesized Speech
Camille Noufi, Lloyd May, Jonathan Berger
The inclusion of voice persona in synthesized voice can be significant in a broad range of human-computer-interaction (HCI) applications, including augmentative and assistive commu…
Acoustically-Driven Phoneme Removal That Preserves Vocal Affect Cues
Camille Noufi, Jonathan Berger, Karen J. Parker +1
In this paper, we propose a method for removing linguistic information from speech for the purpose of isolating paralinguistic indicators of affect. The immediate utility of this m…
Reconstructing the Dynamic Directivity of Unconstrained Speech
Camille Noufi, Dejan Markovic, Peter Dodds
This article presents a method for estimating and reconstructing the spatial energy distribution pattern of natural speech, which is crucial for achieving realistic vocal presence…
Self-Supervised Learning of Context-Aware Pitch Prosody Representations
Camille Noufi, Prateek Verma
In music and speech, meaning is derived at multiple levels of context. Affect, for example, can be inferred both by a short sound token and by sonic patterns over a longer temporal…