Kamper, Herman
- Participatory Research for Low-resourced Machine Translation: A Case\n Study in African Languages
2020/10/05 by Wilhelmina Nekoto, Vukosi Marivate, Nekoto, Wilhelmina +92 · 16 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Software Engineering Research #Topic Modeling
- Voice Conversion With Just Nearest Neighbors
2023/05/30 by Matthew Baas, Benjamin van Niekerk, Baas, Matthew +3 · 16 citations
Computer Science · #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Music and Audio Processing #Sound (cs.SD) #Speech Recognition and Synthesis #Speech and Audio Processing #electronic engineering #information engineering
- Masakhane -- Machine Translation For Africa
2020/03/13 by Iroro Orife, Orife, Iroro, Julia Kreutzer +47 · 9 citations
Computer Science · Social Sciences · #Natural Language Processing Techniques #Topic Modeling #Wikis in Education and Collaboration
- Vector-quantized neural networks for acoustic unit discovery in the ZeroSpeech 2020 challenge
2020/05/19 by van Niekerk, Benjamin, Nortje, Leanne, Kamper, Herman · 4 citations
#Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #electronic engineering #information engineering
- Pre-training on high-resource speech recognition improves low-resource\n speech-to-text translation
2018/09/05 by Sameer Bansal, Bansal, Sameer, Herman Kamper +7 · 3 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Speech Recognition and Synthesis #Topic Modeling
- An embedded segmental K-means model for unsupervised segmentation and\n clustering of speech
2017/03/23 by Herman Kamper, Karen Livescu, Kamper, Herman +3 · 3 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Speech Recognition and Synthesis #Speech and Audio Processing
- Analyzing Speaker Information in Self-Supervised Models to Improve Zero-Resource Speech Processing
2021/08/02 by van Niekerk, Benjamin, Nortje, Leanne, Baas, Matthew +1 · 2 citations
#Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #electronic engineering #information engineering
- Deep convolutional acoustic word embeddings using word-pair side\n information
2015/10/05 by Herman Kamper, Kamper, Herman, Weiran Wang +3 · 2 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Music and Audio Processing #Speech Recognition and Synthesis #Speech and Audio Processing #Topic Modeling
- Acoustic word embeddings for zero-resource languages using self-supervised contrastive learning and multilingual adaptation
2021/03/19 by Jacobs, Christiaan, Matusevych, Yevgen, Kamper, Herman · 2 citations
#Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #electronic engineering #information engineering
- Query-by-Example Search with Discriminative Neural Acoustic Word\n Embeddings
2017/06/12 by Shane Settle, Keith Levin, Settle, Shane +5 · 1 citation
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Music and Audio Processing #Speech Recognition and Synthesis #Time Series Analysis and Forecasting
- Truly unsupervised acoustic word embeddings using weak top-down constraints in encoder-decoder models
2018/11/01 by Kamper, Herman · 1 citation
#Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Sound (cs.SD) #electronic engineering #information engineering
- Improved acoustic word embeddings for zero-resource languages using\n multilingual transfer
2020/06/02 by Herman Kamper, Yevgen Matusevych, Kamper, Herman +3 · 1 citation
Computer Science · #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Music and Audio Processing #Sound (cs.SD) #Speech Recognition and Synthesis #Speech and Audio Processing #electronic engineering #information engineering
- A Correspondence Variational Autoencoder for Unsupervised Acoustic Word Embeddings
2020/12/03 by Puyuan Peng, Herman Kamper, Peng, Puyuan +3 · 1 citation
Computer Science · #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Music and Audio Processing #Sound (cs.SD) #Speech Recognition and Synthesis #Topic Modeling #electronic engineering #information engineering
- A phonetic model of non-native spoken word processing
2021/01/27 by Matusevych, Yevgen, Kamper, Herman, Schatz, Thomas +2 · 1 citation
#Computation and Language (cs.CL) #FOS: Computer and information sciences
- Voice Conversion Can Improve ASR in Very Low-Resource Settings
2021/11/04 by Baas, Matthew, Kamper, Herman · 1 citation
#Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #electronic engineering #information engineering
- Fast ASR-free and almost zero-resource keyword spotting using DTW and CNNs for humanitarian monitoring
2018/06/25 by Menon, Raghav, Kamper, Herman, Quinn, John +1 · 1 citation
#Computation and Language (cs.CL) #FOS: Computer and information sciences
- TransFusion: Transcribing Speech with Multinomial Diffusion
2022/10/14 by Matthew Baas, Kevin Eloff, Baas, Matthew +3 · 1 citation
Computer Science · #Artificial Intelligence (cs.AI) #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Music and Audio Processing #Natural Language Processing Techniques #Sound (cs.SD) #Speech Recognition and Synthesis #electronic engineering #information engineering
- Towards hate speech detection in low-resource languages: Comparing ASR to acoustic word embeddings on Wolof and Swahili
2023/06/01 by Jacobs, Christiaan, Rakotonirina, Nathanaël Carraz, Chimoto, Everlyn Asiko +2 · 1 citation
#Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #electronic engineering #information engineering
- Spoken-Term Discovery using Discrete Speech Units
2024/08/26 by Benjamin van Niekerk, van Niekerk, Benjamin, Julian Zaïdi +5 · 3 citations
Computer Science · #Speech and dialogue systems #Natural Language Processing Techniques
- Speech Recognition for Automatically Assessing Afrikaans and isiXhosa Preschool Oral Narratives
2025/01/11 by Jacobs, Christiaan, Smith, Annelien, Klop, Daleen +3 · 3 citations
#Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #electronic engineering #information engineering
- Critical initialisation for deep signal propagation in noisy rectifier\n neural networks
2018/11/01 by Arnu Pretorius, Elan van Biljon, Pretorius, Arnu +5 · 2 citations
Computer Science · #Machine Learning and ELM #Stochastic Gradient Optimization Techniques #Neural Networks and Applications
- Spoken Language Modeling with Duration-Penalized Self-Supervised Units
2025/05/29 by Visser, Nicol, Kamper, Herman · 2 citations
#Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #electronic engineering #information engineering
- Leveraging multilingual transfer for unsupervised semantic acoustic word embeddings
2023/07/05 by Jacobs, Christiaan, Kamper, Herman · 1 citation
#Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #electronic engineering #information engineering
- MARS6: A Small and Robust Hierarchical-Codec Text-to-Speech Model
2025/01/10 by Matthew Baas, Pieter Scholtz, Baas, Matthew +7 · 1 citation
Computer Science · #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Natural Language Processing Techniques #Speech Recognition and Synthesis #electronic engineering #information engineering