Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Herman Kamper

Herman Kamper

A Temporal Extension of Latent Dirichlet Allocation for Unsupervised Acoustic Unit Discovery



Werner van der Merwe , Herman Kamper , Johan du Preez

Figure 1 for A Temporal Extension of Latent Dirichlet Allocation for Unsupervised Acoustic Unit Discovery
Figure 2 for A Temporal Extension of Latent Dirichlet Allocation for Unsupervised Acoustic Unit Discovery
Figure 3 for A Temporal Extension of Latent Dirichlet Allocation for Unsupervised Acoustic Unit Discovery
Figure 4 for A Temporal Extension of Latent Dirichlet Allocation for Unsupervised Acoustic Unit Discovery

   Access Paper or Ask Questions

Word Segmentation on Discovered Phone Units with Dynamic Programming and Self-Supervised Scoring



Herman Kamper

Figure 1 for Word Segmentation on Discovered Phone Units with Dynamic Programming and Self-Supervised Scoring
Figure 2 for Word Segmentation on Discovered Phone Units with Dynamic Programming and Self-Supervised Scoring
Figure 3 for Word Segmentation on Discovered Phone Units with Dynamic Programming and Self-Supervised Scoring
Figure 4 for Word Segmentation on Discovered Phone Units with Dynamic Programming and Self-Supervised Scoring
* 10 pages, 5 figures, 5 tables 
   Access Paper or Ask Questions

Keyword localisation in untranscribed speech using visually grounded speech models



Kayode Olaleye , Dan Oneata , Herman Kamper

Figure 1 for Keyword localisation in untranscribed speech using visually grounded speech models
Figure 2 for Keyword localisation in untranscribed speech using visually grounded speech models
Figure 3 for Keyword localisation in untranscribed speech using visually grounded speech models
Figure 4 for Keyword localisation in untranscribed speech using visually grounded speech models
* 10 figures, 5 tables 
   Access Paper or Ask Questions

Towards Learning to Speak and Hear Through Multi-Agent Communication over a Continuous Acoustic Channel



Kevin Eloff , Arnu Pretorius , Okko Räsänen , Herman A. Engelbrecht , Herman Kamper

Figure 1 for Towards Learning to Speak and Hear Through Multi-Agent Communication over a Continuous Acoustic Channel
Figure 2 for Towards Learning to Speak and Hear Through Multi-Agent Communication over a Continuous Acoustic Channel
Figure 3 for Towards Learning to Speak and Hear Through Multi-Agent Communication over a Continuous Acoustic Channel
Figure 4 for Towards Learning to Speak and Hear Through Multi-Agent Communication over a Continuous Acoustic Channel
* 12 pages, 6 figures, 3 tables; under review as a conference paper at ICLR 2022 
   Access Paper or Ask Questions

Voice Conversion Can Improve ASR in Very Low-Resource Settings



Matthew Baas , Herman Kamper

Figure 1 for Voice Conversion Can Improve ASR in Very Low-Resource Settings
Figure 2 for Voice Conversion Can Improve ASR in Very Low-Resource Settings
Figure 3 for Voice Conversion Can Improve ASR in Very Low-Resource Settings
Figure 4 for Voice Conversion Can Improve ASR in Very Low-Resource Settings
* 5 page, 4 tables, 2 figures. Submitted to ICASSP 2022 
   Access Paper or Ask Questions

A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion



Benjamin van Niekerk , Marc-André Carbonneau , Julian Zaïdi , Mathew Baas , Hugo Seuté , Herman Kamper

Figure 1 for A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion
Figure 2 for A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion
Figure 3 for A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion
Figure 4 for A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion
* 5 pages, 2 figures, 2 tables. Submitted to ICASSP 2022 
   Access Paper or Ask Questions

Feature learning for efficient ASR-free keyword spotting in low-resource languages



Ewald van der Westhuizen , Herman Kamper , Raghav Menon , John Quinn , Thomas Niesler

Figure 1 for Feature learning for efficient ASR-free keyword spotting in low-resource languages
Figure 2 for Feature learning for efficient ASR-free keyword spotting in low-resource languages
Figure 3 for Feature learning for efficient ASR-free keyword spotting in low-resource languages
Figure 4 for Feature learning for efficient ASR-free keyword spotting in low-resource languages
* 37 pages, 14 figures, Preprint accepted for publication in Computer Speech and Language 
   Access Paper or Ask Questions

Analyzing Speaker Information in Self-Supervised Models to Improve Zero-Resource Speech Processing



Benjamin van Niekerk , Leanne Nortje , Matthew Baas , Herman Kamper

Figure 1 for Analyzing Speaker Information in Self-Supervised Models to Improve Zero-Resource Speech Processing
Figure 2 for Analyzing Speaker Information in Self-Supervised Models to Improve Zero-Resource Speech Processing
Figure 3 for Analyzing Speaker Information in Self-Supervised Models to Improve Zero-Resource Speech Processing
Figure 4 for Analyzing Speaker Information in Self-Supervised Models to Improve Zero-Resource Speech Processing
* Accepted to Interspeech 2021 
   Access Paper or Ask Questions

Mava: a research framework for distributed multi-agent reinforcement learning



Arnu Pretorius , Kale-ab Tessera , Andries P. Smit , Claude Formanek , St John Grimbly , Kevin Eloff , Siphelele Danisa , Lawrence Francis , Jonathan Shock , Herman Kamper , Willie Brink , Herman Engelbrecht , Alexandre Laterre , Karim Beguir

Figure 1 for Mava: a research framework for distributed multi-agent reinforcement learning
Figure 2 for Mava: a research framework for distributed multi-agent reinforcement learning
Figure 3 for Mava: a research framework for distributed multi-agent reinforcement learning
Figure 4 for Mava: a research framework for distributed multi-agent reinforcement learning
* 12 pages, 6 figures 
   Access Paper or Ask Questions
1
2
3
4
5
6
>>