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

StarGAN-ZSVC: Towards Zero-Shot Voice Conversion in Low-Resource Contexts


May 31, 2021
Matthew Baas, Herman Kamper

Figure 1 for StarGAN-ZSVC: Towards Zero-Shot Voice Conversion in Low-Resource Contexts
Figure 2 for StarGAN-ZSVC: Towards Zero-Shot Voice Conversion in Low-Resource Contexts
Figure 3 for StarGAN-ZSVC: Towards Zero-Shot Voice Conversion in Low-Resource Contexts
Figure 4 for StarGAN-ZSVC: Towards Zero-Shot Voice Conversion in Low-Resource Contexts
* In: Springer Communications in Computer and Information Science, Artificial Intelligence Research (SACAIR 2021), vol. 1342, pp. 69-84, 2020 
 * 16 pages, 3 figures. Published in Springer Communications in Computer and Information Science, Artificial Intelligence Research (SACAIR 2021), vol. 1342, pp. 69-84, 2020 
  Access Paper or Ask Questions

Acoustic word embeddings for zero-resource languages using self-supervised contrastive learning and multilingual adaptation


Mar 19, 2021
Christiaan Jacobs, Yevgen Matusevych, Herman Kamper

Figure 1 for Acoustic word embeddings for zero-resource languages using self-supervised contrastive learning and multilingual adaptation
Figure 2 for Acoustic word embeddings for zero-resource languages using self-supervised contrastive learning and multilingual adaptation
Figure 3 for Acoustic word embeddings for zero-resource languages using self-supervised contrastive learning and multilingual adaptation
Figure 4 for Acoustic word embeddings for zero-resource languages using self-supervised contrastive learning and multilingual adaptation
* Accepted to SLT 2021 
  Access Paper or Ask Questions

A phonetic model of non-native spoken word processing


Jan 27, 2021
Yevgen Matusevych, Herman Kamper, Thomas Schatz, Naomi H. Feldman, Sharon Goldwater

Figure 1 for A phonetic model of non-native spoken word processing
Figure 2 for A phonetic model of non-native spoken word processing
Figure 3 for A phonetic model of non-native spoken word processing
Figure 4 for A phonetic model of non-native spoken word processing
* Accepted for publication in Proceedings of EACL-2021. 11 pages, 5 figures, 2 tables 
  Access Paper or Ask Questions

Towards unsupervised phone and word segmentation using self-supervised vector-quantized neural networks


Dec 14, 2020
Herman Kamper, Benjamin van Niekerk

Figure 1 for Towards unsupervised phone and word segmentation using self-supervised vector-quantized neural networks
Figure 2 for Towards unsupervised phone and word segmentation using self-supervised vector-quantized neural networks
Figure 3 for Towards unsupervised phone and word segmentation using self-supervised vector-quantized neural networks
Figure 4 for Towards unsupervised phone and word segmentation using self-supervised vector-quantized neural networks
* 5 pages, 3 figures, 5 tables 
  Access Paper or Ask Questions

Towards localisation of keywords in speech using weak supervision


Dec 14, 2020
Kayode Olaleye, Benjamin van Niekerk, Herman Kamper

* Accepted to NeurIPS-SAS 
  Access Paper or Ask Questions

A comparison of self-supervised speech representations as input features for unsupervised acoustic word embeddings


Dec 14, 2020
Lisa van Staden, Herman Kamper

Figure 1 for A comparison of self-supervised speech representations as input features for unsupervised acoustic word embeddings
Figure 2 for A comparison of self-supervised speech representations as input features for unsupervised acoustic word embeddings
Figure 3 for A comparison of self-supervised speech representations as input features for unsupervised acoustic word embeddings
Figure 4 for A comparison of self-supervised speech representations as input features for unsupervised acoustic word embeddings
* Accepted to SLT 2021 
  Access Paper or Ask Questions

Direct multimodal few-shot learning of speech and images


Dec 10, 2020
Leanne Nortje, Herman Kamper

Figure 1 for Direct multimodal few-shot learning of speech and images
Figure 2 for Direct multimodal few-shot learning of speech and images
Figure 3 for Direct multimodal few-shot learning of speech and images
Figure 4 for Direct multimodal few-shot learning of speech and images
* 3 figures, 2 tables 
  Access Paper or Ask Questions

A Correspondence Variational Autoencoder for Unsupervised Acoustic Word Embeddings


Dec 03, 2020
Puyuan Peng, Herman Kamper, Karen Livescu

Figure 1 for A Correspondence Variational Autoencoder for Unsupervised Acoustic Word Embeddings
Figure 2 for A Correspondence Variational Autoencoder for Unsupervised Acoustic Word Embeddings
Figure 3 for A Correspondence Variational Autoencoder for Unsupervised Acoustic Word Embeddings
Figure 4 for A Correspondence Variational Autoencoder for Unsupervised Acoustic Word Embeddings
* 10 pages, 6 figures, NeurIPS 2020 Workshop Self-Supervised Learning for Speech and Audio Processing 
  Access Paper or Ask Questions

Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages


Oct 05, 2020
Wilhelmina Nekoto, Vukosi Marivate, Tshinondiwa Matsila, Timi Fasubaa, Tajudeen Kolawole, Taiwo Fagbohungbe, Solomon Oluwole Akinola, Shamsuddee Hassan Muhammad, Salomon Kabongo, Salomey Osei, Sackey Freshia, Rubungo Andre Niyongabo, Ricky Macharm, Perez Ogayo, Orevaoghene Ahia, Musie Meressa, Mofe Adeyemi, Masabata Mokgesi-Selinga, Lawrence Okegbemi, Laura Jane Martinus, Kolawole Tajudeen, Kevin Degila, Kelechi Ogueji, Kathleen Siminyu, Julia Kreutzer, Jason Webster, Jamiil Toure Ali, Jade Abbott, Iroro Orife, Ignatius Ezeani, Idris Abdulkabir Dangana, Herman Kamper, Hady Elsahar, Goodness Duru, Ghollah Kioko, Espoir Murhabazi, Elan van Biljon, Daniel Whitenack, Christopher Onyefuluchi, Chris Emezue, Bonaventure Dossou, Blessing Sibanda, Blessing Itoro Bassey, Ayodele Olabiyi, Arshath Ramkilowan, Alp Öktem, Adewale Akinfaderin, Abdallah Bashir

Figure 1 for Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages
Figure 2 for Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages
Figure 3 for Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages
Figure 4 for Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages
* Findings of EMNLP 2020 
  Access Paper or Ask Questions

Unsupervised vs. transfer learning for multimodal one-shot matching of speech and images


Aug 14, 2020
Leanne Nortje, Herman Kamper

Figure 1 for Unsupervised vs. transfer learning for multimodal one-shot matching of speech and images
Figure 2 for Unsupervised vs. transfer learning for multimodal one-shot matching of speech and images
Figure 3 for Unsupervised vs. transfer learning for multimodal one-shot matching of speech and images
Figure 4 for Unsupervised vs. transfer learning for multimodal one-shot matching of speech and images
* Accepted at Interspeech 2020 
  Access Paper or Ask Questions

Evaluating computational models of infant phonetic learning across languages


Aug 06, 2020
Yevgen Matusevych, Thomas Schatz, Herman Kamper, Naomi H. Feldman, Sharon Goldwater

* 2020. In S. Denison, M. Mack, Y. Xu, and B. Armstrong (Eds.), Proceedings of the 42nd Annual Conference of the Cognitive Science Society (pp. 571-577). Austin, TX: Cognitive Science Society 
 * 7 pages, 1 figure 
  Access Paper or Ask Questions

Improved acoustic word embeddings for zero-resource languages using multilingual transfer


Jun 02, 2020
Herman Kamper, Yevgen Matusevych, Sharon Goldwater

Figure 1 for Improved acoustic word embeddings for zero-resource languages using multilingual transfer
Figure 2 for Improved acoustic word embeddings for zero-resource languages using multilingual transfer
Figure 3 for Improved acoustic word embeddings for zero-resource languages using multilingual transfer
Figure 4 for Improved acoustic word embeddings for zero-resource languages using multilingual transfer
* 11 pages, 7 figures, 8 tables. arXiv admin note: text overlap with arXiv:2002.02109 
  Access Paper or Ask Questions

Vector-quantized neural networks for acoustic unit discovery in the ZeroSpeech 2020 challenge


May 19, 2020
Benjamin van Niekerk, Leanne Nortje, Herman Kamper

Figure 1 for Vector-quantized neural networks for acoustic unit discovery in the ZeroSpeech 2020 challenge
Figure 2 for Vector-quantized neural networks for acoustic unit discovery in the ZeroSpeech 2020 challenge
Figure 3 for Vector-quantized neural networks for acoustic unit discovery in the ZeroSpeech 2020 challenge
Figure 4 for Vector-quantized neural networks for acoustic unit discovery in the ZeroSpeech 2020 challenge
* 5 pages, 3 figures, 2 tables 
  Access Paper or Ask Questions

Analyzing autoencoder-based acoustic word embeddings


Apr 03, 2020
Yevgen Matusevych, Herman Kamper, Sharon Goldwater

Figure 1 for Analyzing autoencoder-based acoustic word embeddings
Figure 2 for Analyzing autoencoder-based acoustic word embeddings
Figure 3 for Analyzing autoencoder-based acoustic word embeddings
Figure 4 for Analyzing autoencoder-based acoustic word embeddings
* 6 pages, 7 figures, accepted to BAICS workshop (ICLR2020) 
  Access Paper or Ask Questions

Unsupervised feature learning for speech using correspondence and Siamese networks


Mar 28, 2020
Petri-Johan Last, Herman A. Engelbrecht, Herman Kamper

Figure 1 for Unsupervised feature learning for speech using correspondence and Siamese networks
Figure 2 for Unsupervised feature learning for speech using correspondence and Siamese networks
Figure 3 for Unsupervised feature learning for speech using correspondence and Siamese networks
Figure 4 for Unsupervised feature learning for speech using correspondence and Siamese networks
* IEEE Signal Processing Letters 27 (2020) 421-425 
 * 5 pages, 3 figures, 2 tables; accepted to the IEEE Signal Processing Letters, (c) 2020 IEEE 
  Access Paper or Ask Questions

Masakhane -- Machine Translation For Africa


Mar 13, 2020
Iroro Orife, Julia Kreutzer, Blessing Sibanda, Daniel Whitenack, Kathleen Siminyu, Laura Martinus, Jamiil Toure Ali, Jade Abbott, Vukosi Marivate, Salomon Kabongo, Musie Meressa, Espoir Murhabazi, Orevaoghene Ahia, Elan van Biljon, Arshath Ramkilowan, Adewale Akinfaderin, Alp Öktem, Wole Akin, Ghollah Kioko, Kevin Degila, Herman Kamper, Bonaventure Dossou, Chris Emezue, Kelechi Ogueji, Abdallah Bashir

Figure 1 for Masakhane -- Machine Translation For Africa
* Accepted for the AfricaNLP Workshop, ICLR 2020 
  Access Paper or Ask Questions

Multilingual acoustic word embedding models for processing zero-resource languages


Feb 21, 2020
Herman Kamper, Yevgen Matusevych, Sharon Goldwater

Figure 1 for Multilingual acoustic word embedding models for processing zero-resource languages
Figure 2 for Multilingual acoustic word embedding models for processing zero-resource languages
Figure 3 for Multilingual acoustic word embedding models for processing zero-resource languages
Figure 4 for Multilingual acoustic word embedding models for processing zero-resource languages
* 5 pages, 4 figures, 1 table; accepted to ICASSP 2020. arXiv admin note: text overlap with arXiv:1811.00403 
  Access Paper or Ask Questions

Deep motion estimation for parallel inter-frame prediction in video compression


Dec 11, 2019
André Nortje, Herman A. Engelbrecht, Herman Kamper

Figure 1 for Deep motion estimation for parallel inter-frame prediction in video compression
Figure 2 for Deep motion estimation for parallel inter-frame prediction in video compression
Figure 3 for Deep motion estimation for parallel inter-frame prediction in video compression
Figure 4 for Deep motion estimation for parallel inter-frame prediction in video compression
* 25 pages, 11 figures, 5 tables 
  Access Paper or Ask Questions

BINet: a binary inpainting network for deep patch-based image compression


Dec 11, 2019
André Nortje, Willie Brink, Herman A. Engelbrecht, Herman Kamper

Figure 1 for BINet: a binary inpainting network for deep patch-based image compression
Figure 2 for BINet: a binary inpainting network for deep patch-based image compression
Figure 3 for BINet: a binary inpainting network for deep patch-based image compression
Figure 4 for BINet: a binary inpainting network for deep patch-based image compression
* 19 pages, 16 figures, 3 tables 
  Access Paper or Ask Questions

If dropout limits trainable depth, does critical initialisation still matter? A large-scale statistical analysis on ReLU networks


Oct 13, 2019
Arnu Pretorius, Elan van Biljon, Benjamin van Niekerk, Ryan Eloff, Matthew Reynard, Steve James, Benjamin Rosman, Herman Kamper, Steve Kroon

Figure 1 for If dropout limits trainable depth, does critical initialisation still matter? A large-scale statistical analysis on ReLU networks
Figure 2 for If dropout limits trainable depth, does critical initialisation still matter? A large-scale statistical analysis on ReLU networks
Figure 3 for If dropout limits trainable depth, does critical initialisation still matter? A large-scale statistical analysis on ReLU networks
Figure 4 for If dropout limits trainable depth, does critical initialisation still matter? A large-scale statistical analysis on ReLU networks
* 8 pages, 6 figures, preliminary work 
  Access Paper or Ask Questions

On the expected behaviour of noise regularised deep neural networks as Gaussian processes


Oct 12, 2019
Arnu Pretorius, Herman Kamper, Steve Kroon

Figure 1 for On the expected behaviour of noise regularised deep neural networks as Gaussian processes
Figure 2 for On the expected behaviour of noise regularised deep neural networks as Gaussian processes
Figure 3 for On the expected behaviour of noise regularised deep neural networks as Gaussian processes
Figure 4 for On the expected behaviour of noise regularised deep neural networks as Gaussian processes
* 8 pages, 6 figures, preliminary work 
  Access Paper or Ask Questions

Classifying topics in speech when all you have is crummy translations


Aug 29, 2019
Sameer Bansal, Herman Kamper, Adam Lopez, Sharon Goldwater

Figure 1 for Classifying topics in speech when all you have is crummy translations
Figure 2 for Classifying topics in speech when all you have is crummy translations
Figure 3 for Classifying topics in speech when all you have is crummy translations
Figure 4 for Classifying topics in speech when all you have is crummy translations

  Access Paper or Ask Questions

On the Contributions of Visual and Textual Supervision in Low-resource Semantic Speech Retrieval


Apr 24, 2019
Ankita Pasad, Bowen Shi, Herman Kamper, Karen Livescu

Figure 1 for On the Contributions of Visual and Textual Supervision in Low-resource Semantic Speech Retrieval
Figure 2 for On the Contributions of Visual and Textual Supervision in Low-resource Semantic Speech Retrieval
Figure 3 for On the Contributions of Visual and Textual Supervision in Low-resource Semantic Speech Retrieval

  Access Paper or Ask Questions

Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networks


Apr 16, 2019
Ryan Eloff, André Nortje, Benjamin van Niekerk, Avashna Govender, Leanne Nortje, Arnu Pretorius, Elan van Biljon, Ewald van der Westhuizen, Lisa van Staden, Herman Kamper

Figure 1 for Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networks
Figure 2 for Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networks
Figure 3 for Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networks
* 5 pages, 2 figures, 2 tables 
  Access Paper or Ask Questions

Semantic query-by-example speech search using visual grounding


Apr 15, 2019
Herman Kamper, Aristotelis Anastassiou, Karen Livescu

Figure 1 for Semantic query-by-example speech search using visual grounding
Figure 2 for Semantic query-by-example speech search using visual grounding
Figure 3 for Semantic query-by-example speech search using visual grounding
Figure 4 for Semantic query-by-example speech search using visual grounding
* Accepted to ICASSP 2019 
  Access Paper or Ask Questions

Almost Zero-Resource ASR-free Keyword Spotting using Multilingual Bottleneck Features and Correspondence Autoencoders


Nov 14, 2018
Raghav Menon, Herman Kamper, John Quinn, Thomas Niesler

Figure 1 for Almost Zero-Resource ASR-free Keyword Spotting using Multilingual Bottleneck Features and Correspondence Autoencoders
Figure 2 for Almost Zero-Resource ASR-free Keyword Spotting using Multilingual Bottleneck Features and Correspondence Autoencoders
Figure 3 for Almost Zero-Resource ASR-free Keyword Spotting using Multilingual Bottleneck Features and Correspondence Autoencoders
Figure 4 for Almost Zero-Resource ASR-free Keyword Spotting using Multilingual Bottleneck Features and Correspondence Autoencoders
* 5 pages, 2 figures, 2 tables, Submitted to ICASSP 2019 
  Access Paper or Ask Questions

Multimodal One-Shot Learning of Speech and Images


Nov 09, 2018
Ryan Eloff, Herman A. Engelbrecht, Herman Kamper

Figure 1 for Multimodal One-Shot Learning of Speech and Images
Figure 2 for Multimodal One-Shot Learning of Speech and Images
Figure 3 for Multimodal One-Shot Learning of Speech and Images
Figure 4 for Multimodal One-Shot Learning of Speech and Images
* 5 pages, 1 figure, 3 tables 
  Access Paper or Ask Questions

Multilingual and Unsupervised Subword Modeling for Zero-Resource Languages


Nov 09, 2018
Enno Hermann, Herman Kamper, Sharon Goldwater

Figure 1 for Multilingual and Unsupervised Subword Modeling for Zero-Resource Languages
Figure 2 for Multilingual and Unsupervised Subword Modeling for Zero-Resource Languages
Figure 3 for Multilingual and Unsupervised Subword Modeling for Zero-Resource Languages
Figure 4 for Multilingual and Unsupervised Subword Modeling for Zero-Resource Languages
* 11 pages, 5 figures, 7 tables. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible. arXiv admin note: substantial text overlap with arXiv:1803.08863 
  Access Paper or Ask Questions

Truly unsupervised acoustic word embeddings using weak top-down constraints in encoder-decoder models


Nov 01, 2018
Herman Kamper

Figure 1 for Truly unsupervised acoustic word embeddings using weak top-down constraints in encoder-decoder models
Figure 2 for Truly unsupervised acoustic word embeddings using weak top-down constraints in encoder-decoder models
Figure 3 for Truly unsupervised acoustic word embeddings using weak top-down constraints in encoder-decoder models
Figure 4 for Truly unsupervised acoustic word embeddings using weak top-down constraints in encoder-decoder models
* 5 pages, 3 figures, 2 tables 
  Access Paper or Ask Questions