Alert button
Picture for Herman Kamper

Herman Kamper

Alert button

Mitigating Catastrophic Forgetting for Few-Shot Spoken Word Classification Through Meta-Learning

May 22, 2023
Ruan van der Merwe, Herman Kamper

Figure 1 for Mitigating Catastrophic Forgetting for Few-Shot Spoken Word Classification Through Meta-Learning
Figure 2 for Mitigating Catastrophic Forgetting for Few-Shot Spoken Word Classification Through Meta-Learning
Figure 3 for Mitigating Catastrophic Forgetting for Few-Shot Spoken Word Classification Through Meta-Learning
Figure 4 for Mitigating Catastrophic Forgetting for Few-Shot Spoken Word Classification Through Meta-Learning
Viaarxiv icon

TransFusion: Transcribing Speech with Multinomial Diffusion

Oct 14, 2022
Matthew Baas, Kevin Eloff, Herman Kamper

Figure 1 for TransFusion: Transcribing Speech with Multinomial Diffusion
Figure 2 for TransFusion: Transcribing Speech with Multinomial Diffusion
Figure 3 for TransFusion: Transcribing Speech with Multinomial Diffusion
Figure 4 for TransFusion: Transcribing Speech with Multinomial Diffusion
Viaarxiv icon

Towards visually prompted keyword localisation for zero-resource spoken languages

Oct 12, 2022
Leanne Nortje, Herman Kamper

Figure 1 for Towards visually prompted keyword localisation for zero-resource spoken languages
Figure 2 for Towards visually prompted keyword localisation for zero-resource spoken languages
Figure 3 for Towards visually prompted keyword localisation for zero-resource spoken languages
Figure 4 for Towards visually prompted keyword localisation for zero-resource spoken languages
Viaarxiv icon

YFACC: A Yorùbá speech-image dataset for cross-lingual keyword localisation through visual grounding

Oct 12, 2022
Kayode Olaleye, Dan Oneata, Herman Kamper

Figure 1 for YFACC: A Yorùbá speech-image dataset for cross-lingual keyword localisation through visual grounding
Figure 2 for YFACC: A Yorùbá speech-image dataset for cross-lingual keyword localisation through visual grounding
Figure 3 for YFACC: A Yorùbá speech-image dataset for cross-lingual keyword localisation through visual grounding
Figure 4 for YFACC: A Yorùbá speech-image dataset for cross-lingual keyword localisation through visual grounding
Viaarxiv icon

GAN You Hear Me? Reclaiming Unconditional Speech Synthesis from Diffusion Models

Oct 11, 2022
Matthew Baas, Herman Kamper

Figure 1 for GAN You Hear Me? Reclaiming Unconditional Speech Synthesis from Diffusion Models
Figure 2 for GAN You Hear Me? Reclaiming Unconditional Speech Synthesis from Diffusion Models
Figure 3 for GAN You Hear Me? Reclaiming Unconditional Speech Synthesis from Diffusion Models
Figure 4 for GAN You Hear Me? Reclaiming Unconditional Speech Synthesis from Diffusion Models
Viaarxiv icon

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

Jun 29, 2022
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
Viaarxiv icon

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

Feb 24, 2022
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
Viaarxiv icon

Keyword localisation in untranscribed speech using visually grounded speech models

Feb 02, 2022
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
Viaarxiv icon

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

Nov 04, 2021
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
Viaarxiv icon