Herman Kamper
Identifiers
- name variant Herman Kamper 0.60 · backfill
Papers (24)
- Revisiting Lexicon Evaluation in Unsupervised Word Discovery eess.AS · 2026 · author #3
- Interpreting Speaker Characteristics in the Dimensions of Self-Supervised Speech Features eess.AS · 2026 · author #3
- Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networks cs.CL · 2019 · author #10
- Semantic query-by-example speech search using visual grounding cs.CL · 2019 · author #1
- Feature exploration for almost zero-resource ASR-free keyword spotting using a multilingual bottleneck extractor and correspondence autoencoders eess.AS · 2018 · author #2
- Multimodal One-Shot Learning of Speech and Images cs.CL · 2018 · author #3
- Truly unsupervised acoustic word embeddings using weak top-down constraints in encoder-decoder models cs.CL · 2018 · author #1
- Critical initialisation for deep signal propagation in noisy rectifier neural networks stat.ML · 2018 · author #4
- Pre-training on high-resource speech recognition improves low-resource speech-to-text translation cs.CL · 2018 · author #2
- ASR-free CNN-DTW keyword spotting using multilingual bottleneck features for almost zero-resource languages cs.CL · 2018 · author #2
- Fast ASR-free and almost zero-resource keyword spotting using DTW and CNNs for humanitarian monitoring cs.CL · 2018 · author #2
- Learning Dynamics of Linear Denoising Autoencoders stat.ML · 2018 · author #3
- Visually grounded cross-lingual keyword spotting in speech cs.CL · 2018 · author #1
- Low-Resource Speech-to-Text Translation cs.CL · 2018 · author #2
- Semantic speech retrieval with a visually grounded model of untranscribed speech cs.CL · 2017 · author #1
- Query-by-Example Search with Discriminative Neural Acoustic Word Embeddings cs.CL · 2017 · author #3
- Visually grounded learning of keyword prediction from untranscribed speech cs.CL · 2017 · author #1
- An embedded segmental K-means model for unsupervised segmentation and clustering of speech cs.CL · 2017 · author #1
- Towards speech-to-text translation without speech recognition cs.CL · 2017 · author #2
- Unsupervised neural and Bayesian models for zero-resource speech processing cs.CL · 2017 · author #1
- Weakly supervised spoken term discovery using cross-lingual side information cs.CL · 2016 · author #2
- A segmental framework for fully-unsupervised large-vocabulary speech recognition cs.CL · 2016 · author #1
- Unsupervised word segmentation and lexicon discovery using acoustic word embeddings cs.CL · 2016 · author #1
- Deep convolutional acoustic word embeddings using word-pair side information cs.CL · 2015 · author #1
Mentions
- 1510.01032 #1 · backfill · confidence 0.70 Herman Kamper
- 2606.06183 #3 · arxiv_oai · confidence 0.70 Herman Kamper
Frequent Coauthors
- Karen Livescu 8 shared papers
- Sharon Goldwater 7 shared papers
- Adam Lopez 4 shared papers
- Sameer Bansal 4 shared papers
- Arnu Pretorius 3 shared papers
- John Quinn 3 shared papers
- Raghav Menon 3 shared papers
- Thomas Niesler 3 shared papers
- Aren Jansen 2 shared papers
- Benjamin van Niekerk 2 shared papers
- Elan Van Biljon 2 shared papers
- Ewald van der Westhuizen 2 shared papers
- Gregory Shakhnarovich 2 shared papers
- Ryan Eloff 2 shared papers
- Shane Settle 2 shared papers
- Steve Kroon 2 shared papers
- Andr\'e Nortje 1 shared papers
- Aristotelis Anastassiou 1 shared papers
- Avashna Govender 1 shared papers
- Danel Slabbert 1 shared papers