default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDHerman Kamper
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
[j21]Christiaan Jacobs
, Herman Kamper:
Leveraging Multilingual Transfer for Unsupervised Semantic Acoustic Word Embeddings. IEEE Signal Process. Lett. 31: 311-315 (2024)- [j20]Leanne Nortje, Dan Oneata, Yevgen Matusevych, Herman Kamper:
Visually Grounded Speech Models Have a Mutual Exclusivity Bias. Trans. Assoc. Comput. Linguistics 12: 755-770 (2024) - [j19]Matthew Baas, Herman Kamper:
Disentanglement in a GAN for Unconditional Speech Synthesis. IEEE ACM Trans. Audio Speech Lang. Process. 32: 1324-1335 (2024) - [j18]Leanne Nortje, Dan Oneata, Herman Kamper:
Visually Grounded Few-Shot Word Learning in Low-Resource Settings. IEEE ACM Trans. Audio Speech Lang. Process. 32: 2544-2554 (2024) - [i73]Herman Kamper, Benjamin van Niekerk:
Revisiting speech segmentation and lexicon learning with better features. CoRR abs/2401.17902 (2024) - [i72]Leanne Nortje, Dan Oneata, Yevgen Matusevych, Herman Kamper:
Visually Grounded Speech Models have a Mutual Exclusivity Bias. CoRR abs/2403.13922 (2024) - [i71]Dan Oneata, Herman Kamper:
Translating speech with just images. CoRR abs/2406.07133 (2024) - [i70]Leanne Nortje, Dan Oneata, Herman Kamper:
Improved Visually Prompted Keyword Localisation in Real Low-Resource Settings. CoRR abs/2409.06013 (2024) - [i69]Simon Malan, Benjamin van Niekerk, Herman Kamper:
Unsupervised Word Discovery: Boundary Detection with Clustering vs. Dynamic Programming. CoRR abs/2409.14486 (2024) - 2023
- [j17]Urs J. De Swardt, Herman Kamper:
Semi-Supervised Machine Learning for Livestock Threat Classification Using GPS Data. IEEE Access 11: 27749-27758 (2023) - [j16]Yevgen Matusevych, Thomas Schatz, Herman Kamper, Naomi H. Feldman, Sharon Goldwater:
Infant Phonetic Learning as Perceptual Space Learning: A Crosslinguistic Evaluation of Computational Models. Cogn. Sci. 47(7) (2023) - [j15]Benjamin van Niekerk, Marc-André Carbonneau, Herman Kamper:
Rhythm Modeling for Voice Conversion. IEEE Signal Process. Lett. 30: 1297-1301 (2023) - [j14]Herman Kamper:
Word Segmentation on Discovered Phone Units With Dynamic Programming and Self-Supervised Scoring. IEEE ACM Trans. Audio Speech Lang. Process. 31: 684-694 (2023) - [c54]Christiaan Jacobs, Nathanaël Carraz Rakotonirina, Everlyn Asiko Chimoto, Bruce A. Bassett, Herman Kamper:
Towards hate speech detection in low-resource languages: Comparing ASR to acoustic word embeddings on Wolof and Swahili. INTERSPEECH 2023: 436-440 - [c53]Ruan van der Merwe, Herman Kamper:
Mitigating Catastrophic Forgetting for Few-Shot Spoken Word Classification Through Meta-Learning. INTERSPEECH 2023: 441-445 - [c52]Matthew Baas, Benjamin van Niekerk, Herman Kamper:
Voice Conversion With Just Nearest Neighbors. INTERSPEECH 2023: 2053-2057 - [c51]Leanne Nortje, Benjamin van Niekerk, Herman Kamper:
Visually grounded few-shot word acquisition with fewer shots. INTERSPEECH 2023: 3412-3416 - [i68]Ruan van der Merwe, Herman Kamper:
Mitigating Catastrophic Forgetting for Few-Shot Spoken Word Classification Through Meta-Learning. CoRR abs/2305.13080 (2023) - [i67]Leanne Nortje, Benjamin van Niekerk, Herman Kamper:
Visually grounded few-shot word acquisition with fewer shots. CoRR abs/2305.15937 (2023) - [i66]Matthew Baas, Benjamin van Niekerk, Herman Kamper:
Voice Conversion With Just Nearest Neighbors. CoRR abs/2305.18975 (2023) - [i65]Christiaan Jacobs, Nathanaël Carraz Rakotonirina, Everlyn Asiko Chimoto, Bruce A. Bassett, Herman Kamper:
Towards hate speech detection in low-resource languages: Comparing ASR to acoustic word embeddings on Wolof and Swahili. CoRR abs/2306.00410 (2023) - [i64]Leanne Nortje, Dan Oneata, Herman Kamper:
Visually grounded few-shot word learning in low-resource settings. CoRR abs/2306.11371 (2023) - [i63]Matthew Baas, Herman Kamper:
Disentanglement in a GAN for Unconditional Speech Synthesis. CoRR abs/2307.01673 (2023) - [i62]Christiaan Jacobs, Herman Kamper:
Leveraging multilingual transfer for unsupervised semantic acoustic word embeddings. CoRR abs/2307.02083 (2023) - [i61]Benjamin van Niekerk, Marc-André Carbonneau, Herman Kamper:
Rhythm Modeling for Voice Conversion. CoRR abs/2307.06040 (2023) - [i60]Matthew Baas, Herman Kamper:
Voice Conversion for Stuttered Speech, Instruments, Unseen Languages and Textually Described Voices. CoRR abs/2310.08104 (2023) - 2022
- [j13]Ewald van der Westhuizen, Herman Kamper, Raghav Menon, John A. Quinn, Thomas Niesler:
Feature learning for efficient ASR-free keyword spotting in low-resource languages. Comput. Speech Lang. 71: 101275 (2022) - [j12]Kayode Olaleye, Dan Oneata, Herman Kamper:
Keyword Localisation in Untranscribed Speech Using Visually Grounded Speech Models. IEEE J. Sel. Top. Signal Process. 16(6): 1454-1466 (2022) - [c50]Benjamin van Niekerk, Marc-André Carbonneau, Julian Zaïdi, Matthew Baas, Hugo Seuté, Herman Kamper:
A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion. ICASSP 2022: 6562-6566 - [c49]Werner van der Merwe, Herman Kamper, Johan Adam du Preez:
A Temporal Extension of Latent Dirichlet Allocation for Unsupervised Acoustic Unit Discovery. INTERSPEECH 2022: 1426-1430 - [c48]Matthew Baas, Herman Kamper:
Voice Conversion Can Improve ASR in Very Low-Resource Settings. INTERSPEECH 2022: 3513-3517 - [c47]Matthew Baas, Kevin Eloff, Herman Kamper:
TransFusion: Transcribing Speech with Multinomial Diffusion. SACAIR 2022: 231-245 - [c46]Leanne Nortje, Herman Kamper:
Towards Visually Prompted Keyword Localisation for Zero-Resource Spoken Languages. SLT 2022: 700-707 - [c45]Kayode Olaleye, Dan Oneata, Herman Kamper:
YFACC: A Yorùbá Speech-Image Dataset for Cross-Lingual Keyword Localisation Through Visual Grounding. SLT 2022: 731-738 - [c44]Matthew Baas, Herman Kamper:
GAN You Hear Me? Reclaiming Unconditional Speech Synthesis from Diffusion Models. SLT 2022: 906-911 - [i59]Kayode Olaleye, Dan Oneata, Herman Kamper:
Keyword localisation in untranscribed speech using visually grounded speech models. CoRR abs/2202.01107 (2022) - [i58]Herman Kamper:
Word Segmentation on Discovered Phone Units with Dynamic Programming and Self-Supervised Scoring. CoRR abs/2202.11929 (2022) - [i57]Werner van der Merwe, Herman Kamper, Johan A. du Preez:
A Temporal Extension of Latent Dirichlet Allocation for Unsupervised Acoustic Unit Discovery. CoRR abs/2206.11706 (2022) - [i56]Kayode Olaleye, Dan Oneata, Herman Kamper:
YFACC: A Yorùbá speech-image dataset for cross-lingual keyword localisation through visual grounding. CoRR abs/2210.04600 (2022) - [i55]Matthew Baas, Herman Kamper:
GAN You Hear Me? Reclaiming Unconditional Speech Synthesis from Diffusion Models. CoRR abs/2210.05271 (2022) - [i54]Leanne Nortje, Herman Kamper:
Towards visually prompted keyword localisation for zero-resource spoken languages. CoRR abs/2210.06229 (2022) - [i53]Matthew Baas, Kevin Eloff, Herman Kamper:
TransFusion: Transcribing Speech with Multinomial Diffusion. CoRR abs/2210.07677 (2022) - 2021
- [j11]Enno Hermann, Herman Kamper, Sharon Goldwater:
Multilingual and unsupervised subword modeling for zero-resource languages. Comput. Speech Lang. 65: 101098 (2021) - [j10]André Nortje, Willie Brink, Herman A. Engelbrecht, Herman Kamper:
BINet: A binary inpainting network for deep patch-based image compression. Signal Process. Image Commun. 92: 116119 (2021) - [j9]Herman Kamper, Yevgen Matusevych, Sharon Goldwater:
Improved Acoustic Word Embeddings for Zero-Resource Languages Using Multilingual Transfer. IEEE ACM Trans. Audio Speech Lang. Process. 29: 1107-1118 (2021) - [c43]Yevgen Matusevych, Herman Kamper, Thomas Schatz, Naomi Feldman, Sharon Goldwater:
A phonetic model of non-native spoken word processing. EACL 2021: 1480-1490 - [c42]Herman Kamper, Benjamin van Niekerk:
Towards Unsupervised Phone and Word Segmentation Using Self-Supervised Vector-Quantized Neural Networks. Interspeech 2021: 1539-1543 - [c41]Christiaan Jacobs, Herman Kamper:
Multilingual Transfer of Acoustic Word Embeddings Improves When Training on Languages Related to the Target Zero-Resource Language. Interspeech 2021: 1549-1553 - [c40]Benjamin van Niekerk, Leanne Nortje, Matthew Baas, Herman Kamper:
Analyzing Speaker Information in Self-Supervised Models to Improve Zero-Resource Speech Processing. Interspeech 2021: 1554-1558 - [c39]Leanne Nortje, Herman Kamper:
Direct Multimodal Few-Shot Learning of Speech and Images. Interspeech 2021: 2971-2975 - [c38]Kayode Olaleye, Herman Kamper:
Attention-Based Keyword Localisation in Speech Using Visual Grounding. Interspeech 2021: 2991-2995 - [c37]Christiaan Jacobs, Yevgen Matusevych, Herman Kamper:
Acoustic Word Embeddings for Zero-Resource Languages Using Self-Supervised Contrastive Learning and Multilingual Adaptation. SLT 2021: 919-926 - [c36]Lisa van Staden, Herman Kamper:
A Comparison of Self-Supervised Speech Representations As Input Features For Unsupervised Acoustic Word Embeddings. SLT 2021: 927-934 - [i52]Yevgen Matusevych, Herman Kamper, Thomas Schatz, Naomi H. Feldman, Sharon Goldwater:
A phonetic model of non-native spoken word processing. CoRR abs/2101.11332 (2021) - [i51]Christiaan Jacobs, Yevgen Matusevych, Herman Kamper:
Acoustic word embeddings for zero-resource languages using self-supervised contrastive learning and multilingual adaptation. CoRR abs/2103.10731 (2021) - [i50]Matthew Baas, Herman Kamper:
StarGAN-ZSVC: Towards Zero-Shot Voice Conversion in Low-Resource Contexts. CoRR abs/2106.00043 (2021) - [i49]Kayode Olaleye, Herman Kamper:
Attention-Based Keyword Localisation in Speech using Visual Grounding. CoRR abs/2106.08859 (2021) - [i48]Christiaan Jacobs, Herman Kamper:
Multilingual transfer of acoustic word embeddings improves when training on languages related to the target zero-resource language. CoRR abs/2106.12834 (2021) - [i47]Arnu Pretorius, Kale-ab Tessera, Andries P. Smit, Claude Formanek, St John Grimbly, Kevin Eloff, Siphelele Danisa, Lawrence Francis, Jonathan P. Shock, Herman Kamper, Willie Brink, Herman A. Engelbrecht, Alexandre Laterre, Karim Beguir:
Mava: a research framework for distributed multi-agent reinforcement learning. CoRR abs/2107.01460 (2021) - [i46]Benjamin van Niekerk, Leanne Nortje, Matthew Baas, Herman Kamper:
Analyzing Speaker Information in Self-Supervised Models to Improve Zero-Resource Speech Processing. CoRR abs/2108.00917 (2021) - [i45]Benjamin van Niekerk, Marc-André Carbonneau, Julian Zaïdi, Matthew Baas, Hugo Seuté, Herman Kamper:
A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion. CoRR abs/2111.02392 (2021) - [i44]Matthew Baas, Herman Kamper:
Voice Conversion Can Improve ASR in Very Low-Resource Settings. CoRR abs/2111.02674 (2021) - [i43]Kevin Eloff, Arnu Pretorius, Okko Räsänen, Herman A. Engelbrecht, Herman Kamper:
Towards Learning to Speak and Hear Through Multi-Agent Communication over a Continuous Acoustic Channel. CoRR abs/2111.02827 (2021) - 2020
- [j8]Arnu Pretorius, Herman Kamper, Steve Kroon:
On the expected behaviour of noise regularised deep neural networks as Gaussian processes. Pattern Recognit. Lett. 138: 75-81 (2020) - [j7]Arnu Pretorius, Elan Van Biljon, Benjamin van Niekerk, Ryan Eloff, Matthew Reynard, Steven James, Benjamin Rosman, Herman Kamper, Steve Kroon:
If dropout limits trainable depth, does critical initialisation still matter? A large-scale statistical analysis on ReLU networks. Pattern Recognit. Lett. 138: 95-105 (2020) - [j6]Petri-Johan Last, Herman A. Engelbrecht, Herman Kamper:
Unsupervised Feature Learning for Speech Using Correspondence and Siamese Networks. IEEE Signal Process. Lett. 27: 421-425 (2020) - [c35]Yevgen Matusevych, Thomas Schatz, Herman Kamper, Naomi Feldman, Sharon Goldwater:
Evaluating computational models of infant phonetic learning across languages. CogSci 2020 - [c34]Wilhelmina Nekoto, Vukosi Marivate, Tshinondiwa Matsila, Timi E. Fasubaa, Taiwo Fagbohungbe, Solomon Oluwole Akinola, Shamsuddeen Hassan Muhammad, Salomon Kabongo Kabenamualu, Salomey Osei, Freshia Sackey, Rubungo Andre Niyongabo, Ricky Macharm, Perez Ogayo, Orevaoghene Ahia, Musie Meressa Berhe, Mofetoluwa Adeyemi, Masabata Mokgesi-Selinga, Lawrence Okegbemi, Laura Martinus, Kolawole Tajudeen, Kevin Degila, Kelechi Ogueji, Kathleen Siminyu, Julia Kreutzer, Jason Webster, Jamiil Toure Ali, Jade Z. 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 Chinenye Emezue, Bonaventure F. P. Dossou, Blessing K. Sibanda, Blessing Itoro Bassey, Ayodele Olabiyi, Arshath Ramkilowan, Alp Öktem, Adewale Akinfaderin, Abdallah Bashir:
Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages. EMNLP (Findings) 2020: 2144-2160 - [c33]Herman Kamper, Yevgen Matusevych, Sharon Goldwater:
Multilingual Acoustic Word Embedding Models for Processing Zero-resource Languages. ICASSP 2020: 6414-6418 - [c32]Sameer Bansal, Herman Kamper, Adam Lopez, Sharon Goldwater:
Cross-Lingual Topic Prediction For Speech Using Translations. ICASSP 2020: 8164-8168 - [c31]Leanne Nortje, Herman Kamper:
Unsupervised vs. Transfer Learning for Multimodal One-Shot Matching of Speech and Images. INTERSPEECH 2020: 2712-2716 - [c30]Benjamin van Niekerk, Leanne Nortje, Herman Kamper:
Vector-Quantized Neural Networks for Acoustic Unit Discovery in the ZeroSpeech 2020 Challenge. INTERSPEECH 2020: 4836-4840 - [c29]Matthew Baas, Herman Kamper:
StarGAN-ZSVC: Towards Zero-Shot Voice Conversion in Low-Resource Contexts. SACAIR 2020: 69-84 - [c28]Iroro Orife, Julia Kreutzer, Blessing K. Sibanda, Daniel Whitenack, Kathleen Siminyu, Laura Martinus, Jamiil Toure Ali, Jade Z. 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:
Masakhane - Machine Translation For Africa. AfricaNLP 2020 - [i42]Herman Kamper, Yevgen Matusevych, Sharon Goldwater:
Multilingual acoustic word embedding models for processing zero-resource languages. CoRR abs/2002.02109 (2020) - [i41]Petri-Johan Last, Herman A. Engelbrecht, Herman Kamper:
Unsupervised feature learning for speech using correspondence and Siamese networks. CoRR abs/2003.12799 (2020) - [i40]Yevgen Matusevych, Herman Kamper, Sharon Goldwater:
Analyzing autoencoder-based acoustic word embeddings. CoRR abs/2004.01647 (2020) - [i39]Benjamin van Niekerk, Leanne Nortje, Herman Kamper:
Vector-quantized neural networks for acoustic unit discovery in the ZeroSpeech 2020 challenge. CoRR abs/2005.09409 (2020) - [i38]Herman Kamper, Yevgen Matusevych, Sharon Goldwater:
Improved acoustic word embeddings for zero-resource languages using multilingual transfer. CoRR abs/2006.02295 (2020) - [i37]Yevgen Matusevych, Thomas Schatz, Herman Kamper, Naomi H. Feldman, Sharon Goldwater:
Evaluating computational models of infant phonetic learning across languages. CoRR abs/2008.02888 (2020) - [i36]Leanne Nortje, Herman Kamper:
Unsupervised vs. transfer learning for multimodal one-shot matching of speech and images. CoRR abs/2008.06258 (2020) - [i35]Wilhelmina Nekoto, Vukosi Marivate, Tshinondiwa Matsila, Timi E. Fasubaa, Tajudeen Kolawole, Taiwo Fagbohungbe, Solomon Oluwole Akinola, Shamsuddeen 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 Z. 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 K. Sibanda, Blessing Itoro Bassey, Ayodele Olabiyi, Arshath Ramkilowan, Alp Öktem, Adewale Akinfaderin, Abdallah Bashir:
Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages. CoRR abs/2010.02353 (2020) - [i34]Puyuan Peng, Herman Kamper, Karen Livescu:
A Correspondence Variational Autoencoder for Unsupervised Acoustic Word Embeddings. CoRR abs/2012.02221 (2020) - [i33]Leanne Nortje, Herman Kamper:
Direct multimodal few-shot learning of speech and images. CoRR abs/2012.05680 (2020) - [i32]Lisa van Staden, Herman Kamper:
A comparison of self-supervised speech representations as input features for unsupervised acoustic word embeddings. CoRR abs/2012.07387 (2020) - [i31]Kayode Olaleye, Benjamin van Niekerk, Herman Kamper:
Towards localisation of keywords in speech using weak supervision. CoRR abs/2012.07396 (2020) - [i30]Herman Kamper, Benjamin van Niekerk:
Towards unsupervised phone and word segmentation using self-supervised vector-quantized neural networks. CoRR abs/2012.07551 (2020)
2010 – 2019
- 2019
- [j5]Herman Kamper, Gregory Shakhnarovich, Karen Livescu:
Semantic Speech Retrieval With a Visually Grounded Model of Untranscribed Speech. IEEE ACM Trans. Audio Speech Lang. Process. 27(1): 89-98 (2019) - [c27]Herman Kamper:
Truly Unsupervised Acoustic Word Embeddings Using Weak Top-down Constraints in Encoder-decoder Models. ICASSP 2019: 6535-3539 - [c26]Herman Kamper, Aristotelis Anastassiou, Karen Livescu:
Semantic Query-by-example Speech Search Using Visual Grounding. ICASSP 2019: 7120-7124 - [c25]Ryan Eloff, Herman A. Engelbrecht, Herman Kamper:
Multimodal One-shot Learning of Speech and Images. ICASSP 2019: 8623-8627 - [c24]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:
Unsupervised Acoustic Unit Discovery for Speech Synthesis Using Discrete Latent-Variable Neural Networks. INTERSPEECH 2019: 1103-1107 - [c23]Raghav Menon, Herman Kamper, Ewald van der Westhuizen, John A. Quinn, Thomas Niesler:
Feature Exploration for Almost Zero-Resource ASR-Free Keyword Spotting Using a Multilingual Bottleneck Extractor and Correspondence Autoencoders. INTERSPEECH 2019: 3475-3479 - [c22]Ankita Pasad, Bowen Shi, Herman Kamper, Karen Livescu:
On the Contributions of Visual and Textual Supervision in Low-Resource Semantic Speech Retrieval. INTERSPEECH 2019: 4195-4199 - [c21]Sameer Bansal, Herman Kamper, Karen Livescu, Adam Lopez, Sharon Goldwater:
Pre-training on high-resource speech recognition improves low-resource speech-to-text translation. NAACL-HLT (1) 2019: 58-68 - [i29]Herman Kamper, Aristotelis Anastassiou, Karen Livescu:
Semantic query-by-example speech search using visual grounding. CoRR abs/1904.07078 (2019) - [i28]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:
Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networks. CoRR abs/1904.07556 (2019) - [i27]Ankita Pasad, Bowen Shi, Herman Kamper, Karen Livescu:
On the Contributions of Visual and Textual Supervision in Low-resource Semantic Speech Retrieval. CoRR abs/1904.10947 (2019) - [i26]Sameer Bansal, Herman Kamper, Adam Lopez, Sharon Goldwater:
Classifying topics in speech when all you have is crummy translations. CoRR abs/1908.11425 (2019) - [i25]Arnu Pretorius, Herman Kamper, Steve Kroon:
On the expected behaviour of noise regularised deep neural networks as Gaussian processes. CoRR abs/1910.05563 (2019) - [i24]Arnu Pretorius, Elan Van Biljon, Benjamin van Niekerk, Ryan Eloff, Matthew Reynard, Steven James, Benjamin Rosman, Herman Kamper, Steve Kroon:
If dropout limits trainable depth, does critical initialisation still matter? A large-scale statistical analysis on ReLU networks. CoRR abs/1910.05725 (2019) - [i23]André Nortje, Willie Brink, Herman A. Engelbrecht, Herman Kamper:
BINet: a binary inpainting network for deep patch-based image compression. CoRR abs/1912.05189 (2019) - [i22]André Nortje, Herman A. Engelbrecht, Herman Kamper:
Deep motion estimation for parallel inter-frame prediction in video compression. CoRR abs/1912.05193 (2019) - 2018
- [c20]Herman Kamper, Gregory Shakhnarovich, Karen Livescu:
Semantic Speech Retrieval With a Visually Grounded Model of Untranscribed Speech. CVPR Workshops 2018: 2514-2517 - [c19]Saurabchiand Bhati, Herman Kamper, K. Sri Rama Murty:
Phoneme Based Embedded Segmental K-Means for Unsupervised Term Discovery. ICASSP 2018: 5169-5173 - [c18]Arnu Pretorius, Steve Kroon, Herman Kamper:
Learning Dynamics of Linear Denoising Autoencoders. ICML 2018: 4138-4147 - [c17]Sameer Bansal, Herman Kamper, Karen Livescu, Adam Lopez, Sharon Goldwater:
Low-Resource Speech-to-Text Translation. INTERSPEECH 2018: 1298-1302 - [c16]Raghav Menon, Herman Kamper, John A. Quinn, Thomas Niesler:
Fast ASR-free and Almost Zero-resource Keyword Spotting Using DTW and CNNs for Humanitarian Monitoring. INTERSPEECH 2018: 2608-2612 - [c15]Arnu Pretorius, Elan Van Biljon, Steve Kroon, Herman Kamper:
Critical initialisation for deep signal propagation in noisy rectifier neural networks. NeurIPS 2018: 5722-5731 - [c14]Raghav Menon, Herman Kamper, Emre Yilmaz, John A. Quinn, Thomas Niesler:
ASR-Free CNN-DTW Keyword Spotting Using Multilingual Bottleneck Features for Almost Zero-Resource Languages. SLTU 2018: 182-186 - [c13]Herman Kamper, Michael Roth:
Visually Grounded Cross-Lingual Keyword Spotting in Speech. SLTU 2018: 253-257 - [i21]Sameer Bansal, Herman Kamper, Karen Livescu, Adam Lopez, Sharon Goldwater:
Low-Resource Speech-to-Text Translation. CoRR abs/1803.09164 (2018) - [i20]Herman Kamper, Michael Roth:
Visually grounded cross-lingual keyword spotting in speech. CoRR abs/1806.05030 (2018) - [i19]Arnu Pretorius, Steve Kroon, Herman Kamper:
Learning Dynamics of Linear Denoising Autoencoders. CoRR abs/1806.05413 (2018) - [i18]Raghav Menon, Herman Kamper, John A. Quinn, Thomas Niesler:
Fast ASR-free and almost zero-resource keyword spotting using DTW and CNNs for humanitarian monitoring. CoRR abs/1806.09374 (2018) - [i17]Raghav Menon, Herman Kamper, Emre Yilmaz, John A. Quinn, Thomas Niesler:
ASR-free CNN-DTW keyword spotting using multilingual bottleneck features for almost zero-resource languages. CoRR abs/1807.08666 (2018) - [i16]Sameer Bansal, Herman Kamper, Karen Livescu, Adam Lopez, Sharon Goldwater:
Pre-training on high-resource speech recognition improves low-resource speech-to-text translation. CoRR abs/1809.01431 (2018) - [i15]Arnu Pretorius, Elan Van Biljon, Steve Kroon, Herman Kamper:
Critical initialisation for deep signal propagation in noisy rectifier neural networks. CoRR abs/1811.00293 (2018) - [i14]Herman Kamper:
Truly unsupervised acoustic word embeddings using weak top-down constraints in encoder-decoder models. CoRR abs/1811.00403 (2018) - [i13]Ryan Eloff, Herman A. Engelbrecht, Herman Kamper:
Multimodal One-Shot Learning of Speech and Images. CoRR abs/1811.03875 (2018) - [i12]Enno Hermann, Herman Kamper, Sharon Goldwater:
Multilingual and Unsupervised Subword Modeling for Zero-Resource Languages. CoRR abs/1811.04791 (2018) - [i11]Raghav Menon, Herman Kamper, John A. Quinn, Thomas Niesler:
Almost Zero-Resource ASR-free Keyword Spotting using Multilingual Bottleneck Features and Correspondence Autoencoders. CoRR abs/1811.08284 (2018) - 2017
- [b1]Herman Kamper:
Unsupervised neural and Bayesian models for zero-resource speech processing. University of Edinburgh, UK, 2017 - [j4]Herman Kamper, Aren Jansen, Sharon Goldwater:
A segmental framework for fully-unsupervised large-vocabulary speech recognition. Comput. Speech Lang. 46: 154-174 (2017) - [c12]Herman Kamper, Karen Livescu, Sharon Goldwater:
An embedded segmental K-means model for unsupervised segmentation and clustering of speech. ASRU 2017: 719-726 - [c11]Sameer Bansal, Herman Kamper, Adam Lopez, Sharon Goldwater:
Towards speech-to-text translation without speech recognition. EACL (2) 2017: 474-479 - [c10]Sameer Bansal, Herman Kamper, Sharon Goldwater, Adam Lopez:
Weakly supervised spoken term discovery using cross-lingual side information. ICASSP 2017: 5760-5764 - [c9]Shane Settle, Keith D. Levin, Herman Kamper, Karen Livescu:
Query-by-Example Search with Discriminative Neural Acoustic Word Embeddings. INTERSPEECH 2017: 2874-2878 - [c8]Herman Kamper, Shane Settle, Gregory Shakhnarovich, Karen Livescu:
Visually Grounded Learning of Keyword Prediction from Untranscribed Speech. INTERSPEECH 2017: 3677-3681 - [i10]Herman Kamper:
Unsupervised neural and Bayesian models for zero-resource speech processing. CoRR abs/1701.00851 (2017) - [i9]Sameer Bansal, Herman Kamper, Adam Lopez, Sharon Goldwater:
Towards speech-to-text translation without speech recognition. CoRR abs/1702.03856 (2017) - [i8]Herman Kamper, Karen Livescu, Sharon Goldwater:
An embedded segmental k-means model for unsupervised segmentation and clustering of speech. CoRR abs/1703.08135 (2017) - [i7]Herman Kamper, Shane Settle, Gregory Shakhnarovich, Karen Livescu:
Visually grounded learning of keyword prediction from untranscribed speech. CoRR abs/1703.08136 (2017) - [i6]Shane Settle, Keith D. Levin, Herman Kamper, Karen Livescu:
Query-by-Example Search with Discriminative Neural Acoustic Word Embeddings. CoRR abs/1706.03818 (2017) - [i5]Herman Kamper, Gregory Shakhnarovich, Karen Livescu:
Semantic keyword spotting by learning from images and speech. CoRR abs/1710.01949 (2017) - 2016
- [j3]Herman Kamper, Aren Jansen, Sharon Goldwater:
Unsupervised Word Segmentation and Lexicon Discovery Using Acoustic Word Embeddings. IEEE ACM Trans. Audio Speech Lang. Process. 24(4): 669-679 (2016) - [c7]Herman Kamper, Weiran Wang, Karen Livescu:
Deep convolutional acoustic word embeddings using word-pair side information. ICASSP 2016: 4950-4954 - [i4]Herman Kamper, Aren Jansen, Sharon Goldwater:
Unsupervised word segmentation and lexicon discovery using acoustic word embeddings. CoRR abs/1603.02845 (2016) - [i3]Herman Kamper, Aren Jansen, Sharon Goldwater:
A segmental framework for fully-unsupervised large-vocabulary speech recognition. CoRR abs/1606.06950 (2016) - [i2]Sameer Bansal, Herman Kamper, Sharon Goldwater, Adam Lopez:
Weakly supervised spoken term discovery using cross-lingual side information. CoRR abs/1609.06530 (2016) - 2015
- [c6]Herman Kamper, Micha Elsner, Aren Jansen, Sharon Goldwater:
Unsupervised neural network based feature extraction using weak top-down constraints. ICASSP 2015: 5818-5822 - [c5]Herman Kamper, Aren Jansen, Sharon Goldwater:
Fully unsupervised small-vocabulary speech recognition using a segmental Bayesian model. INTERSPEECH 2015: 678-682 - [c4]Daniel Renshaw, Herman Kamper, Aren Jansen, Sharon Goldwater:
A comparison of neural network methods for unsupervised representation learning on the zero resource speech challenge. INTERSPEECH 2015: 3199-3203 - [i1]Herman Kamper, Weiran Wang, Karen Livescu:
Deep convolutional acoustic word embeddings using word-pair side information. CoRR abs/1510.01032 (2015) - 2014
- [j2]Herman Kamper, Febe de Wet, Thomas Hain, Thomas Niesler:
Capitalising on North American speech resources for the development of a South African English large vocabulary speech recognition system. Comput. Speech Lang. 28(6): 1255-1268 (2014) - [c3]Herman Kamper, Aren Jansen, Simon King, Sharon Goldwater:
Unsupervised lexical clustering of speech segments using fixed-dimensional acoustic embeddings. SLT 2014: 100-105 - 2012
- [j1]Herman Kamper, Félicien Jeje Muamba Mukanya, Thomas Niesler:
Multi-accent acoustic modelling of South African English. Speech Commun. 54(6): 801-813 (2012) - [c2]Herman Kamper, Febe de Wet, Thomas Hain, Thomas Niesler:
Resource development and experiments in automatic south african broadcast news transcription. SLTU 2012: 102-106 - 2011
- [c1]Herman Kamper, Thomas Niesler:
Multi-Accent Speech Recognition of Afrikaans, Black and White Varieties of South African English. INTERSPEECH 2011: 3189-3192
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-11-05 21:59 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
