Herman Kamper

Stellenbosch University — South Africa

Computer Science · Physical Sciences

18h-index1.6kcitations180works0.72yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Speech Recognition and Synthesis(105), Music and Audio Processing(55), Natural Language Processing Techniques(48), Speech and Audio Processing(44), Topic Modeling(39)

Publications179 total

Improved visually prompted keyword localisation in real low-resource settings
2025
Unsupervised lexicon learning from speech is limited by representations rather than clustering
ArXiv.org·2025Open Access
Towards few-shot isolated word reading assessment
2025
Automatically assessing oral narratives of Afrikaans and isiXhosa children
2025
Spoken Language Modeling with Duration-Penalized Self-Supervised Units
2025
LinearVC: Linear Transformations of Self-Supervised Features Through the Lens of Voice Conversion
2025
The mutual exclusivity bias of bilingual visually grounded speech models
2025Open Access
Should Top-Down Clustering Affect Boundaries in Unsupervised Word Discovery?
arXiv (Cornell University)·2025Open Access
Feature-based analysis of oral narratives from Afrikaans and isiXhosa children
arXiv (Cornell University)·2025Open Access
Automatically assessing oral narratives of Afrikaans and isiXhosa children
arXiv (Cornell University)·2025Open Access
Towards few-shot isolated word reading assessment
arXiv (Cornell University)·2025Open Access
The mutual exclusivity bias of bilingual visually grounded speech models
arXiv (Cornell University)·2025Open Access
LinearVC: Linear transformations of self-supervised features through the lens of voice conversion
arXiv (Cornell University)·2025Open Access
Spoken Language Modeling with Duration-Penalized Self-Supervised Units
arXiv (Cornell University)·2025Open Access
Unsupervised Word Discovery: Boundary Detection with Clustering vs. Dynamic Programming
2025· 1 cited
Speech Recognition for Automatically Assessing Afrikaans and isiXhosa Preschool Oral Narratives
2025
MARS6: A Small and Robust Hierarchical-Codec Text-to-Speech Model
2025
MARS6: A Small and Robust Hierarchical-Codec Text-to-Speech Model
arXiv (Cornell University)·2025Open Access
Unsupervised Word Discovery: Boundary Detection with Clustering vs. Dynamic Programming
arXiv (Cornell University)·2024Open Access
Improved Visually Prompted Keyword Localisation in Real Low-Resource Settings
arXiv (Cornell University)·2024Open Access
page 1 of 9Next →

Frequent Co-authors

Sharon Goldwater(16), Karen Livescu(10), Aren Jansen(7), Matthew Baas(6), Benjamin van Niekerk(5), Elan van Biljon(5), Sameer Bansal(4), Adam Lopez(4), Leanne Nortje(4), Kolawole Tajudeen(4), Arnu Pretorius(4), Gregory Shakhnarovich(3), Iroro Orife(3), Julia Kreutzer(3), Blessing Sibanda(3), Daniel Whitenack(3), Kathleen Siminyu(3), Laura Martinus(3), Jamiil Touré Ali(3), Jade Abbott(3)