Herman Kamper - RankMe

170 papers A* 2A 29B 1C 1Misc 13Journal 106Unranked 17

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Interpreting Speaker Characteristics in the Dimensions of Self-Supervised Speech Features. CoRR Kyle Janse van Rensburg, Benjamin van Niekerk, Herman Kamper
2026	J	`jnl`	ZeroSyl: Simple Zero-Resource Syllable Tokenization for Spoken Language Modeling. CoRR Nicol Visser, Simon Malan, Danel Slabbert, Herman Kamper
2025	J	`jnl`	Analyzing and Improving Speaker Similarity Assessment for Speech Synthesis. CoRR Marc-André Carbonneau, Benjamin van Niekerk, Hugo Seuté, Jean-Philippe Letendre, Herman Kamper, Julian Zaïdi
2025	J	`jnl`	Automatically assessing oral narratives of Afrikaans and isiXhosa children. CoRR Retief Louw, Emma Sharratt, Febe de Wet, Christiaan Jacobs, Annelien Smith, Herman Kamper
2025	J	`jnl`	Feature-based analysis of oral narratives from Afrikaans and isiXhosa children. CoRR Emma Sharratt, Annelien Smith, Retief Louw, Daleen Klop, Febe de Wet, Herman Kamper
2025	—	`conf`	Improved visually prompted keyword localisation in real low-resource settings. SpeD Leanne Nortje, Dan Oneata, Gabriel Pirlogeanu, Herman Kamper
2025	A	`conf`	LinearVC: Linear Transformations of Self-Supervised Features Through the Lens of Voice Conversion. INTERSPEECH Herman Kamper, Benjamin van Niekerk, Julian Zaïdi, Marc-André Carbonneau
2025	J	`jnl`	LinearVC: Linear transformations of self-supervised features through the lens of voice conversion. CoRR Herman Kamper, Benjamin van Niekerk, Julian Zaïdi, Marc-André Carbonneau
2025	Misc	`conf`	MARS6: A Small and Robust Hierarchical-Codec Text-to-Speech Model. ICASSP Matthew Baas, Pieter Scholtz, Arnav Mehta, Elliott Dyson, Akshat Prakash, Herman Kamper
2025	J	`jnl`	MARS6: A Small and Robust Hierarchical-Codec Text-to-Speech Model. CoRR Matthew Baas, Pieter Scholtz, Arnav Mehta, Elliott Dyson, Akshat Prakash, Herman Kamper
2025	J	`jnl`	Should Top-Down Clustering Affect Boundaries in Unsupervised Word Discovery? CoRR Simon Malan, Benjamin van Niekerk, Herman Kamper
2025	Misc	`conf`	Speech Recognition for Automatically Assessing Afrikaans and isiXhosa Preschool Oral Narratives. ICASSP Christiaan Jacobs, Annelien Smith, Daleen Klop, Ondrej Klejch, Febe de Wet, Herman Kamper
2025	J	`jnl`	Speech Recognition for Automatically Assessing Afrikaans and isiXhosa Preschool Oral Narratives. CoRR Christiaan Jacobs, Annelien Smith, Daleen Klop, Ondrej Klejch, Febe de Wet, Herman Kamper
2025	A	`conf`	Spoken Language Modeling with Duration-Penalized Self-Supervised Units. INTERSPEECH Nicol Visser, Herman Kamper
2025	J	`jnl`	Spoken Language Modeling with Duration-Penalized Self-Supervised Units. CoRR Nicol Visser, Herman Kamper
2025	A	`conf`	The mutual exclusivity bias of bilingual visually grounded speech models. INTERSPEECH Dan Oneata, Leanne Nortje, Yevgen Matusevych, Herman Kamper
2025	J	`jnl`	The mutual exclusivity bias of bilingual visually grounded speech models. CoRR Dan Oneata, Leanne Nortje, Yevgen Matusevych, Herman Kamper
2025	J	`jnl`	Towards few-shot isolated word reading assessment. CoRR Reuben Smit, Retief Louw, Herman Kamper
2025	Misc	`conf`	Unsupervised Word Discovery: Boundary Detection with Clustering vs. Dynamic Programming. ICASSP Simon Malan, Benjamin van Niekerk, Herman Kamper
2025	J	`jnl`	Unsupervised lexicon learning from speech is limited by representations rather than clustering. CoRR Danel Adendorff, Simon Malan, Herman Kamper
2024	J	`jnl`	Disentanglement in a GAN for Unconditional Speech Synthesis. IEEE ACM Trans. Audio Speech Lang. Process. Matthew Baas, Herman Kamper
2024	J	`jnl`	Improved Visually Prompted Keyword Localisation in Real Low-Resource Settings. CoRR Leanne Nortje, Dan Oneata, Herman Kamper
2024	J	`jnl`	Leveraging Multilingual Transfer for Unsupervised Semantic Acoustic Word Embeddings. IEEE Signal Process. Lett. Christiaan Jacobs, Herman Kamper
2024	J	`jnl`	Revisiting speech segmentation and lexicon learning with better features. CoRR Herman Kamper, Benjamin van Niekerk
2024	A	`conf`	Spoken-Term Discovery using Discrete Speech Units. INTERSPEECH Benjamin van Niekerk, Julian Zaïdi, Marc-André Carbonneau, Herman Kamper
2024	A	`conf`	Translating speech with just images. INTERSPEECH Dan Oneata, Herman Kamper
2024	J	`jnl`	Translating speech with just images. CoRR Dan Oneata, Herman Kamper
2024	J	`jnl`	Unsupervised Word Discovery: Boundary Detection with Clustering vs. Dynamic Programming. CoRR Simon Malan, Benjamin van Niekerk, Herman Kamper
2024	J	`jnl`	Visually Grounded Few-Shot Word Learning in Low-Resource Settings. IEEE ACM Trans. Audio Speech Lang. Process. Leanne Nortje, Dan Oneata, Herman Kamper
2024	J	`jnl`	Visually Grounded Speech Models Have a Mutual Exclusivity Bias. Trans. Assoc. Comput. Linguistics Leanne Nortje, Dan Oneata, Yevgen Matusevych, Herman Kamper
2024	J	`jnl`	Visually Grounded Speech Models have a Mutual Exclusivity Bias. CoRR Leanne Nortje, Dan Oneata, Yevgen Matusevych, Herman Kamper
2023	J	`jnl`	Disentanglement in a GAN for Unconditional Speech Synthesis. CoRR Matthew Baas, Herman Kamper
2023	J	`jnl`	Infant Phonetic Learning as Perceptual Space Learning: A Crosslinguistic Evaluation of Computational Models. Cogn. Sci. Yevgen Matusevych, Thomas Schatz, Herman Kamper, Naomi H. Feldman, Sharon Goldwater
2023	J	`jnl`	Leveraging multilingual transfer for unsupervised semantic acoustic word embeddings. CoRR Christiaan Jacobs, Herman Kamper
2023	A	`conf`	Mitigating Catastrophic Forgetting for Few-Shot Spoken Word Classification Through Meta-Learning. INTERSPEECH Ruan van der Merwe, Herman Kamper
2023	J	`jnl`	Mitigating Catastrophic Forgetting for Few-Shot Spoken Word Classification Through Meta-Learning. CoRR Ruan van der Merwe, Herman Kamper
2023	J	`jnl`	Rhythm Modeling for Voice Conversion. CoRR Benjamin van Niekerk, Marc-André Carbonneau, Herman Kamper
2023	J	`jnl`	Rhythm Modeling for Voice Conversion. IEEE Signal Process. Lett. Benjamin van Niekerk, Marc-André Carbonneau, Herman Kamper
2023	J	`jnl`	Semi-Supervised Machine Learning for Livestock Threat Classification Using GPS Data. IEEE Access Urs J. De Swardt, Herman Kamper
2023	A	`conf`	Towards hate speech detection in low-resource languages: Comparing ASR to acoustic word embeddings on Wolof and Swahili. INTERSPEECH Christiaan Jacobs, Nathanaël Carraz Rakotonirina, Everlyn Asiko Chimoto, Bruce A. Bassett, Herman Kamper
2023	J	`jnl`	Towards hate speech detection in low-resource languages: Comparing ASR to acoustic word embeddings on Wolof and Swahili. CoRR Christiaan Jacobs, Nathanaël Carraz Rakotonirina, Everlyn Asiko Chimoto, Bruce A. Bassett, Herman Kamper
2023	A	`conf`	Visually grounded few-shot word acquisition with fewer shots. INTERSPEECH Leanne Nortje, Benjamin van Niekerk, Herman Kamper
2023	J	`jnl`	Visually grounded few-shot word acquisition with fewer shots. CoRR Leanne Nortje, Benjamin van Niekerk, Herman Kamper
2023	J	`jnl`	Visually grounded few-shot word learning in low-resource settings. CoRR Leanne Nortje, Dan Oneata, Herman Kamper
2023	A	`conf`	Voice Conversion With Just Nearest Neighbors. INTERSPEECH Matthew Baas, Benjamin van Niekerk, Herman Kamper
2023	J	`jnl`	Voice Conversion With Just Nearest Neighbors. CoRR Matthew Baas, Benjamin van Niekerk, Herman Kamper
2023	J	`jnl`	Voice Conversion for Stuttered Speech, Instruments, Unseen Languages and Textually Described Voices. CoRR Matthew Baas, Herman Kamper
2023	J	`jnl`	Word Segmentation on Discovered Phone Units With Dynamic Programming and Self-Supervised Scoring. IEEE ACM Trans. Audio Speech Lang. Process. Herman Kamper
2022	Misc	`conf`	A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion. ICASSP Benjamin van Niekerk, Marc-André Carbonneau, Julian Zaïdi, Matthew Baas, Hugo Seuté, Herman Kamper
2022	A	`conf`	A Temporal Extension of Latent Dirichlet Allocation for Unsupervised Acoustic Unit Discovery. INTERSPEECH Werner van der Merwe, Herman Kamper, Johan Adam du Preez
2022	J	`jnl`	A Temporal Extension of Latent Dirichlet Allocation for Unsupervised Acoustic Unit Discovery. CoRR Werner van der Merwe, Herman Kamper, Johan A. du Preez
2022	J	`jnl`	Feature learning for efficient ASR-free keyword spotting in low-resource languages. Comput. Speech Lang. Ewald van der Westhuizen, Herman Kamper, Raghav Menon, John A. Quinn, Thomas Niesler
2022	—	`conf`	GAN You Hear Me? Reclaiming Unconditional Speech Synthesis from Diffusion Models. SLT Matthew Baas, Herman Kamper
2022	J	`jnl`	GAN You Hear Me? Reclaiming Unconditional Speech Synthesis from Diffusion Models. CoRR Matthew Baas, Herman Kamper
2022	J	`jnl`	Keyword Localisation in Untranscribed Speech Using Visually Grounded Speech Models. IEEE J. Sel. Top. Signal Process. Kayode Olaleye, Dan Oneata, Herman Kamper
2022	J	`jnl`	Keyword localisation in untranscribed speech using visually grounded speech models. CoRR Kayode Olaleye, Dan Oneata, Herman Kamper
2022	—	`conf`	Towards Visually Prompted Keyword Localisation for Zero-Resource Spoken Languages. SLT Leanne Nortje, Herman Kamper
2022	J	`jnl`	Towards visually prompted keyword localisation for zero-resource spoken languages. CoRR Leanne Nortje, Herman Kamper
2022	—	`conf`	TransFusion: Transcribing Speech with Multinomial Diffusion. SACAIR Matthew Baas, Kevin Eloff, Herman Kamper
2022	J	`jnl`	TransFusion: Transcribing Speech with Multinomial Diffusion. CoRR Matthew Baas, Kevin Eloff, Herman Kamper
2022	A	`conf`	Voice Conversion Can Improve ASR in Very Low-Resource Settings. INTERSPEECH Matthew Baas, Herman Kamper
2022	J	`jnl`	Word Segmentation on Discovered Phone Units with Dynamic Programming and Self-Supervised Scoring. CoRR Herman Kamper
2022	—	`conf`	YFACC: A Yorùbá Speech-Image Dataset for Cross-Lingual Keyword Localisation Through Visual Grounding. SLT Kayode Olaleye, Dan Oneata, Herman Kamper
2022	J	`jnl`	YFACC: A Yorùbá speech-image dataset for cross-lingual keyword localisation through visual grounding. CoRR Kayode Olaleye, Dan Oneata, Herman Kamper
2021	J	`jnl`	A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion. CoRR Benjamin van Niekerk, Marc-André Carbonneau, Julian Zaïdi, Matthew Baas, Hugo Seuté, Herman Kamper
2021	—	`conf`	A Comparison of Self-Supervised Speech Representations As Input Features For Unsupervised Acoustic Word Embeddings. SLT Lisa van Staden, Herman Kamper
2021	A	`conf`	A phonetic model of non-native spoken word processing. EACL Yevgen Matusevych, Herman Kamper, Thomas Schatz, Naomi Feldman, Sharon Goldwater
2021	J	`jnl`	A phonetic model of non-native spoken word processing. CoRR Yevgen Matusevych, Herman Kamper, Thomas Schatz, Naomi H. Feldman, Sharon Goldwater
2021	—	`conf`	Acoustic Word Embeddings for Zero-Resource Languages Using Self-Supervised Contrastive Learning and Multilingual Adaptation. SLT Christiaan Jacobs, Yevgen Matusevych, Herman Kamper
2021	J	`jnl`	Acoustic word embeddings for zero-resource languages using self-supervised contrastive learning and multilingual adaptation. CoRR Christiaan Jacobs, Yevgen Matusevych, Herman Kamper
2021	A	`conf`	Analyzing Speaker Information in Self-Supervised Models to Improve Zero-Resource Speech Processing. Interspeech Benjamin van Niekerk, Leanne Nortje, Matthew Baas, Herman Kamper
2021	J	`jnl`	Analyzing Speaker Information in Self-Supervised Models to Improve Zero-Resource Speech Processing. CoRR Benjamin van Niekerk, Leanne Nortje, Matthew Baas, Herman Kamper
2021	A	`conf`	Attention-Based Keyword Localisation in Speech Using Visual Grounding. Interspeech Kayode Olaleye, Herman Kamper
2021	J	`jnl`	Attention-Based Keyword Localisation in Speech using Visual Grounding. CoRR Kayode Olaleye, Herman Kamper
2021	J	`jnl`	BINet: A binary inpainting network for deep patch-based image compression. Signal Process. Image Commun. André Nortje, Willie Brink, Herman A. Engelbrecht, Herman Kamper
2021	A	`conf`	Direct Multimodal Few-Shot Learning of Speech and Images. Interspeech Leanne Nortje, Herman Kamper
2021	J	`jnl`	Improved Acoustic Word Embeddings for Zero-Resource Languages Using Multilingual Transfer. IEEE ACM Trans. Audio Speech Lang. Process. Herman Kamper, Yevgen Matusevych, Sharon Goldwater
2021	A	`conf`	Multilingual Transfer of Acoustic Word Embeddings Improves When Training on Languages Related to the Target Zero-Resource Language. Interspeech Christiaan Jacobs, Herman Kamper
2021	J	`jnl`	Multilingual and unsupervised subword modeling for zero-resource languages. Comput. Speech Lang. Enno Hermann, Herman Kamper, Sharon Goldwater
2021	J	`jnl`	Multilingual transfer of acoustic word embeddings improves when training on languages related to the target zero-resource language. CoRR Christiaan Jacobs, Herman Kamper
2021	J	`jnl`	StarGAN-ZSVC: Towards Zero-Shot Voice Conversion in Low-Resource Contexts. CoRR Matthew Baas, Herman Kamper
2021	J	`jnl`	Towards Learning to Speak and Hear Through Multi-Agent Communication over a Continuous Acoustic Channel. CoRR Kevin Eloff, Arnu Pretorius, Okko Räsänen, Herman A. Engelbrecht, Herman Kamper
2021	A	`conf`	Towards Unsupervised Phone and Word Segmentation Using Self-Supervised Vector-Quantized Neural Networks. Interspeech Herman Kamper, Benjamin van Niekerk
2021	J	`jnl`	Voice Conversion Can Improve ASR in Very Low-Resource Settings. CoRR Matthew Baas, Herman Kamper
2020	J	`jnl`	A Correspondence Variational Autoencoder for Unsupervised Acoustic Word Embeddings. CoRR Puyuan Peng, Herman Kamper, Karen Livescu
2020	J	`jnl`	A comparison of self-supervised speech representations as input features for unsupervised acoustic word embeddings. CoRR Lisa van Staden, Herman Kamper
2020	J	`jnl`	Analyzing autoencoder-based acoustic word embeddings. CoRR Yevgen Matusevych, Herman Kamper, Sharon Goldwater
2020	Misc	`conf`	Cross-Lingual Topic Prediction For Speech Using Translations. ICASSP Sameer Bansal, Herman Kamper, Adam Lopez, Sharon Goldwater
2020	J	`jnl`	Direct multimodal few-shot learning of speech and images. CoRR Leanne Nortje, Herman Kamper
2020	B	`conf`	Evaluating computational models of infant phonetic learning across languages. CogSci Yevgen Matusevych, Thomas Schatz, Herman Kamper, Naomi Feldman, Sharon Goldwater
2020	J	`jnl`	Evaluating computational models of infant phonetic learning across languages. CoRR Yevgen Matusevych, Thomas Schatz, Herman Kamper, Naomi H. Feldman, Sharon Goldwater
2020	J	`jnl`	If dropout limits trainable depth, does critical initialisation still matter? A large-scale statistical analysis on ReLU networks. Pattern Recognit. Lett. Arnu Pretorius, Elan Van Biljon, Benjamin van Niekerk, Ryan Eloff, Matthew Reynard, Steven James, Benjamin Rosman, Herman Kamper, Steve Kroon
2020	J	`jnl`	Improved acoustic word embeddings for zero-resource languages using multilingual transfer. CoRR Herman Kamper, Yevgen Matusevych, Sharon Goldwater
2020	—	`conf`	Masakhane - Machine Translation For Africa. AfricaNLP 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
2020	Misc	`conf`	Multilingual Acoustic Word Embedding Models for Processing Zero-resource Languages. ICASSP Herman Kamper, Yevgen Matusevych, Sharon Goldwater
2020	J	`jnl`	Multilingual acoustic word embedding models for processing zero-resource languages. CoRR Herman Kamper, Yevgen Matusevych, Sharon Goldwater
2020	J	`jnl`	On the expected behaviour of noise regularised deep neural networks as Gaussian processes. Pattern Recognit. Lett. Arnu Pretorius, Herman Kamper, Steve Kroon
2020	—	`conf`	Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages. EMNLP (Findings) 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
2020	J	`jnl`	Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages. CoRR 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
2020	—	`conf`	StarGAN-ZSVC: Towards Zero-Shot Voice Conversion in Low-Resource Contexts. SACAIR Matthew Baas, Herman Kamper
2020	J	`jnl`	Towards localisation of keywords in speech using weak supervision. CoRR Kayode Olaleye, Benjamin van Niekerk, Herman Kamper
2020	J	`jnl`	Towards unsupervised phone and word segmentation using self-supervised vector-quantized neural networks. CoRR Herman Kamper, Benjamin van Niekerk
2020	J	`jnl`	Unsupervised Feature Learning for Speech Using Correspondence and Siamese Networks. IEEE Signal Process. Lett. Petri-Johan Last, Herman A. Engelbrecht, Herman Kamper
2020	J	`jnl`	Unsupervised feature learning for speech using correspondence and Siamese networks. CoRR Petri-Johan Last, Herman A. Engelbrecht, Herman Kamper
2020	A	`conf`	Unsupervised vs. Transfer Learning for Multimodal One-Shot Matching of Speech and Images. INTERSPEECH Leanne Nortje, Herman Kamper
2020	J	`jnl`	Unsupervised vs. transfer learning for multimodal one-shot matching of speech and images. CoRR Leanne Nortje, Herman Kamper
2020	A	`conf`	Vector-Quantized Neural Networks for Acoustic Unit Discovery in the ZeroSpeech 2020 Challenge. INTERSPEECH Benjamin van Niekerk, Leanne Nortje, Herman Kamper
2020	J	`jnl`	Vector-quantized neural networks for acoustic unit discovery in the ZeroSpeech 2020 challenge. CoRR Benjamin van Niekerk, Leanne Nortje, Herman Kamper
2019	J	`jnl`	BINet: a binary inpainting network for deep patch-based image compression. CoRR André Nortje, Willie Brink, Herman A. Engelbrecht, Herman Kamper
2019	J	`jnl`	Classifying topics in speech when all you have is crummy translations. CoRR Sameer Bansal, Herman Kamper, Adam Lopez, Sharon Goldwater
2019	J	`jnl`	Deep motion estimation for parallel inter-frame prediction in video compression. CoRR André Nortje, Herman A. Engelbrecht, Herman Kamper
2019	A	`conf`	Feature Exploration for Almost Zero-Resource ASR-Free Keyword Spotting Using a Multilingual Bottleneck Extractor and Correspondence Autoencoders. INTERSPEECH Raghav Menon, Herman Kamper, Ewald van der Westhuizen, John A. Quinn, Thomas Niesler
2019	J	`jnl`	If dropout limits trainable depth, does critical initialisation still matter? A large-scale statistical analysis on ReLU networks. CoRR Arnu Pretorius, Elan Van Biljon, Benjamin van Niekerk, Ryan Eloff, Matthew Reynard, Steven James, Benjamin Rosman, Herman Kamper, Steve Kroon
2019	Misc	`conf`	Multimodal One-shot Learning of Speech and Images. ICASSP Ryan Eloff, Herman A. Engelbrecht, Herman Kamper
2019	A	`conf`	On the Contributions of Visual and Textual Supervision in Low-Resource Semantic Speech Retrieval. INTERSPEECH Ankita Pasad, Bowen Shi, Herman Kamper, Karen Livescu
2019	J	`jnl`	On the Contributions of Visual and Textual Supervision in Low-resource Semantic Speech Retrieval. CoRR Ankita Pasad, Bowen Shi, Herman Kamper, Karen Livescu
2019	J	`jnl`	On the expected behaviour of noise regularised deep neural networks as Gaussian processes. CoRR Arnu Pretorius, Herman Kamper, Steve Kroon
2019	—	`conf`	Pre-training on high-resource speech recognition improves low-resource speech-to-text translation. NAACL-HLT (1) Sameer Bansal, Herman Kamper, Karen Livescu, Adam Lopez, Sharon Goldwater
2019	Misc	`conf`	Semantic Query-by-example Speech Search Using Visual Grounding. ICASSP Herman Kamper, Aristotelis Anastassiou, Karen Livescu
2019	J	`jnl`	Semantic Speech Retrieval With a Visually Grounded Model of Untranscribed Speech. IEEE ACM Trans. Audio Speech Lang. Process. Herman Kamper, Gregory Shakhnarovich, Karen Livescu
2019	J	`jnl`	Semantic query-by-example speech search using visual grounding. CoRR Herman Kamper, Aristotelis Anastassiou, Karen Livescu
2019	Misc	`conf`	Truly Unsupervised Acoustic Word Embeddings Using Weak Top-down Constraints in Encoder-decoder Models. ICASSP Herman Kamper
2019	A	`conf`	Unsupervised Acoustic Unit Discovery for Speech Synthesis Using Discrete Latent-Variable Neural Networks. INTERSPEECH 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
2019	J	`jnl`	Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networks. CoRR 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
2018	—	`conf`	ASR-Free CNN-DTW Keyword Spotting Using Multilingual Bottleneck Features for Almost Zero-Resource Languages. SLTU Raghav Menon, Herman Kamper, Emre Yilmaz, John A. Quinn, Thomas Niesler
2018	J	`jnl`	ASR-free CNN-DTW keyword spotting using multilingual bottleneck features for almost zero-resource languages. CoRR Raghav Menon, Herman Kamper, Emre Yilmaz, John A. Quinn, Thomas Niesler
2018	J	`jnl`	Almost Zero-Resource ASR-free Keyword Spotting using Multilingual Bottleneck Features and Correspondence Autoencoders. CoRR Raghav Menon, Herman Kamper, John A. Quinn, Thomas Niesler
2018	A*	`conf`	Critical initialisation for deep signal propagation in noisy rectifier neural networks. NeurIPS Arnu Pretorius, Elan Van Biljon, Steve Kroon, Herman Kamper
2018	J	`jnl`	Critical initialisation for deep signal propagation in noisy rectifier neural networks. CoRR Arnu Pretorius, Elan Van Biljon, Steve Kroon, Herman Kamper
2018	A	`conf`	Fast ASR-free and Almost Zero-resource Keyword Spotting Using DTW and CNNs for Humanitarian Monitoring. INTERSPEECH Raghav Menon, Herman Kamper, John A. Quinn, Thomas Niesler
2018	J	`jnl`	Fast ASR-free and almost zero-resource keyword spotting using DTW and CNNs for humanitarian monitoring. CoRR Raghav Menon, Herman Kamper, John A. Quinn, Thomas Niesler
2018	A*	`conf`	Learning Dynamics of Linear Denoising Autoencoders. ICML Arnu Pretorius, Steve Kroon, Herman Kamper
2018	J	`jnl`	Learning Dynamics of Linear Denoising Autoencoders. CoRR Arnu Pretorius, Steve Kroon, Herman Kamper
2018	A	`conf`	Low-Resource Speech-to-Text Translation. INTERSPEECH Sameer Bansal, Herman Kamper, Karen Livescu, Adam Lopez, Sharon Goldwater
2018	J	`jnl`	Low-Resource Speech-to-Text Translation. CoRR Sameer Bansal, Herman Kamper, Karen Livescu, Adam Lopez, Sharon Goldwater
2018	J	`jnl`	Multilingual and Unsupervised Subword Modeling for Zero-Resource Languages. CoRR Enno Hermann, Herman Kamper, Sharon Goldwater
2018	J	`jnl`	Multimodal One-Shot Learning of Speech and Images. CoRR Ryan Eloff, Herman A. Engelbrecht, Herman Kamper
2018	Misc	`conf`	Phoneme Based Embedded Segmental K-Means for Unsupervised Term Discovery. ICASSP Saurabchiand Bhati, Herman Kamper, K. Sri Rama Murty
2018	J	`jnl`	Pre-training on high-resource speech recognition improves low-resource speech-to-text translation. CoRR Sameer Bansal, Herman Kamper, Karen Livescu, Adam Lopez, Sharon Goldwater
2018	—	`conf`	Semantic Speech Retrieval With a Visually Grounded Model of Untranscribed Speech. CVPR Workshops Herman Kamper, Gregory Shakhnarovich, Karen Livescu
2018	J	`jnl`	Truly unsupervised acoustic word embeddings using weak top-down constraints in encoder-decoder models. CoRR Herman Kamper
2018	—	`conf`	Visually Grounded Cross-Lingual Keyword Spotting in Speech. SLTU Herman Kamper, Michael Roth
2018	J	`jnl`	Visually grounded cross-lingual keyword spotting in speech. CoRR Herman Kamper, Michael Roth
2017	J	`jnl`	A segmental framework for fully-unsupervised large-vocabulary speech recognition. Comput. Speech Lang. Herman Kamper, Aren Jansen, Sharon Goldwater
2017	C	`conf`	An embedded segmental K-means model for unsupervised segmentation and clustering of speech. ASRU Herman Kamper, Karen Livescu, Sharon Goldwater
2017	J	`jnl`	An embedded segmental k-means model for unsupervised segmentation and clustering of speech. CoRR Herman Kamper, Karen Livescu, Sharon Goldwater
2017	A	`conf`	Query-by-Example Search with Discriminative Neural Acoustic Word Embeddings. INTERSPEECH Shane Settle, Keith D. Levin, Herman Kamper, Karen Livescu
2017	J	`jnl`	Query-by-Example Search with Discriminative Neural Acoustic Word Embeddings. CoRR Shane Settle, Keith D. Levin, Herman Kamper, Karen Livescu
2017	J	`jnl`	Semantic keyword spotting by learning from images and speech. CoRR Herman Kamper, Gregory Shakhnarovich, Karen Livescu
2017	—	`conf`	Towards speech-to-text translation without speech recognition. EACL (2) Sameer Bansal, Herman Kamper, Adam Lopez, Sharon Goldwater
2017	J	`jnl`	Towards speech-to-text translation without speech recognition. CoRR Sameer Bansal, Herman Kamper, Adam Lopez, Sharon Goldwater
2017	J	`jnl`	Unsupervised neural and Bayesian models for zero-resource speech processing. CoRR Herman Kamper
2017	—	`—`	Unsupervised neural and Bayesian models for zero-resource speech processing. Herman Kamper
2017	A	`conf`	Visually Grounded Learning of Keyword Prediction from Untranscribed Speech. INTERSPEECH Herman Kamper, Shane Settle, Gregory Shakhnarovich, Karen Livescu
2017	J	`jnl`	Visually grounded learning of keyword prediction from untranscribed speech. CoRR Herman Kamper, Shane Settle, Gregory Shakhnarovich, Karen Livescu
2017	Misc	`conf`	Weakly supervised spoken term discovery using cross-lingual side information. ICASSP Sameer Bansal, Herman Kamper, Sharon Goldwater, Adam Lopez
2016	J	`jnl`	A segmental framework for fully-unsupervised large-vocabulary speech recognition. CoRR Herman Kamper, Aren Jansen, Sharon Goldwater
2016	Misc	`conf`	Deep convolutional acoustic word embeddings using word-pair side information. ICASSP Herman Kamper, Weiran Wang, Karen Livescu
2016	J	`jnl`	Unsupervised Word Segmentation and Lexicon Discovery Using Acoustic Word Embeddings. IEEE ACM Trans. Audio Speech Lang. Process. Herman Kamper, Aren Jansen, Sharon Goldwater
2016	J	`jnl`	Unsupervised word segmentation and lexicon discovery using acoustic word embeddings. CoRR Herman Kamper, Aren Jansen, Sharon Goldwater
2016	J	`jnl`	Weakly supervised spoken term discovery using cross-lingual side information. CoRR Sameer Bansal, Herman Kamper, Sharon Goldwater, Adam Lopez
2015	A	`conf`	A comparison of neural network methods for unsupervised representation learning on the zero resource speech challenge. INTERSPEECH Daniel Renshaw, Herman Kamper, Aren Jansen, Sharon Goldwater
2015	J	`jnl`	Deep convolutional acoustic word embeddings using word-pair side information. CoRR Herman Kamper, Weiran Wang, Karen Livescu
2015	A	`conf`	Fully unsupervised small-vocabulary speech recognition using a segmental Bayesian model. INTERSPEECH Herman Kamper, Aren Jansen, Sharon Goldwater
2015	Misc	`conf`	Unsupervised neural network based feature extraction using weak top-down constraints. ICASSP Herman Kamper, Micha Elsner, Aren Jansen, Sharon Goldwater
2014	J	`jnl`	Capitalising on North American speech resources for the development of a South African English large vocabulary speech recognition system. Comput. Speech Lang. Herman Kamper, Febe de Wet, Thomas Hain, Thomas Niesler
2014	—	`conf`	Unsupervised lexical clustering of speech segments using fixed-dimensional acoustic embeddings. SLT Herman Kamper, Aren Jansen, Simon King, Sharon Goldwater
2012	J	`jnl`	Multi-accent acoustic modelling of South African English. Speech Commun. Herman Kamper, Félicien Jeje Muamba Mukanya, Thomas Niesler
2012	—	`conf`	Resource development and experiments in automatic south african broadcast news transcription. SLTU Herman Kamper, Febe de Wet, Thomas Hain, Thomas Niesler
2011	A	`conf`	Multi-Accent Speech Recognition of Afrikaans, Black and White Varieties of South African English. INTERSPEECH Herman Kamper, Thomas Niesler