Camille Noufi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Camille Noufi has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Dejan Markovic
Codec Avatars Lab Meta Pittsburgh PA USA
1 shared publication Jonathan Berger
Center for Computer Research in Music and Acoustics (CCRMA), Stanford University, United States
1 shared publicationLloyd May
Center for Computer Research in Music and Acoustics (CCRMA), Stanford University, United States
1 shared publication- Peter Dodds1 shared publication
- Prateek Verma
Datta Meghe Institute of Higher Education and Research
1 shared publication
Latest Publications
- Open Access
- 29 September 2025
- Published by Frontiers Media SA in Frontiers in Computer Science
- Vol. 7, 1575296
A model of vocal persona: context, perception, production
We present a contextualized production–perception model of vocal persona developed through deductive thematic analysis of interviews with voice and performance experts. Our findings reveal that vocal persona is a dynamic, context-responsive set of vocal behaviors that frames and bounds expressive interactions—both biological and synthesized—while centering the speaker's agency. By examining how experts adapt their vocal output through both broad persona shifts and fine-grained paralinguistic adjustments, our model identifies a key missing mechanism in current approaches to expressive speech synthesis: the integration of high-level persona prompting with detailed paralinguistic control. This work bridges an important gap in the literature on expressive and interactive speech technologies and offers practical insights for improving voice user interfaces and augmentative and alternative communication systems. Incorporating this vocal persona framework into expressive speech synthesis holds the potential to enhance user agency and embodiment during communication, fostering a heightened sense of authenticity and a more intuitive relationship with voice interaction technology and one's environment.
- 29 September 2025
- Published by Frontiers Media SA in Frontiers in Computer Science
- Vol. 7, 1575296
Open AccessA model of vocal persona: context, perception, production
We present a contextualized production–perception model of vocal persona developed through deductive thematic analysis of interviews with voice and performance experts. Our findings reveal that vocal persona is a dynamic, context-responsive set of vocal behaviors that frames and bounds expressive interactions—both biological and synthesized—while centering the speaker's agency. By examining how experts adapt their vocal output through both broad persona shifts and fine-grained paralinguistic adjustments, our model identifies a key missing mechanism in current approaches to expressive speech synthesis: the integration of high-level persona prompting with detailed paralinguistic control. This work bridges an important gap in the literature on expressive and interactive speech technologies and offers practical insights for improving voice user interfaces and augmentative and alternative communication systems. Incorporating this vocal persona framework into expressive speech synthesis holds the potential to enhance user agency and embodiment during communication, fostering a heightened sense of authenticity and a more intuitive relationship with voice interaction technology and one's environment.
- Open Access
Reconstructing the Dynamic Directivity of Unconstrained Speech
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 in virtual communication settings. The method comprises two stages. First, recordings of speech captured by a real, static microphone array are used to create an egocentric virtual array that tracks the movement of the speaker over time. This virtual array is used to measure and encode the high-resolution directivity pattern of the speech signal as it evolves dynamically with natural speech and movement. In the second stage, the encoded directivity representation is utilized to train a machine learning model that can estimate the full, dynamic directivity pattern given a limited set of speech signals, such as those recorded using the microphones on a head-mounted display. Our results show that neural networks can accurately estimate the full directivity pattern of natural, unconstrained speech from limited information. The proposed method for estimating and reconstructing the spatial energy distribution pattern of natural speech, along with the evaluation of various machine learning models and training paradigms, provides an important contribution to the development of realistic vocal presence in virtual communication settings.
Open AccessReconstructing the Dynamic Directivity of Unconstrained Speech
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 in virtual communication settings. The method comprises two stages. First, recordings of speech captured by a real, static microphone array are used to create an egocentric virtual array that tracks the movement of the speaker over time. This virtual array is used to measure and encode the high-resolution directivity pattern of the speech signal as it evolves dynamically with natural speech and movement. In the second stage, the encoded directivity representation is utilized to train a machine learning model that can estimate the full, dynamic directivity pattern given a limited set of speech signals, such as those recorded using the microphones on a head-mounted display. Our results show that neural networks can accurately estimate the full directivity pattern of natural, unconstrained speech from limited information. The proposed method for estimating and reconstructing the spatial energy distribution pattern of natural speech, along with the evaluation of various machine learning models and training paradigms, provides an important contribution to the development of realistic vocal presence in virtual communication settings.
- Open Access
Self-Supervised Learning of Context-Aware Pitch Prosody Representations
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 window such as an entire recording. In this letter, we focus on inferring meaning from this dichotomy of contexts. We show how contextual representations of short sung vocal lines can be implicitly learned from fundamental frequency ($F_0$) and thus be used as a meaningful feature space for downstream Music Information Retrieval (MIR) tasks. We propose three self-supervised deep learning paradigms which leverage pseudotask learning of these two levels of context to produce latent representation spaces. We evaluate the usefulness of these representations by embedding unseen pitch contours into each space and conducting downstream classification tasks. Our results show that contextual representation can enhance downstream classification by as much as 15\% as compared to using traditional statistical contour features.
Open AccessSelf-Supervised Learning of Context-Aware Pitch Prosody Representations
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 window such as an entire recording. In this letter, we focus on inferring meaning from this dichotomy of contexts. We show how contextual representations of short sung vocal lines can be implicitly learned from fundamental frequency ($F_0$) and thus be used as a meaningful feature space for downstream Music Information Retrieval (MIR) tasks. We propose three self-supervised deep learning paradigms which leverage pseudotask learning of these two levels of context to produce latent representation spaces. We evaluate the usefulness of these representations by embedding unseen pitch contours into each space and conducting downstream classification tasks. Our results show that contextual representation can enhance downstream classification by as much as 15\% as compared to using traditional statistical contour features.