Prati
Herman Kamper
Herman Kamper
Stellenbosch University
Potvrđena adresa e-pošte na sun.ac.za - Početna stranica
Naslov
Citirano
Citirano
Godina
Pre-training on high-resource speech recognition improves low-resource speech-to-text translation
S Bansal, H Kamper, K Livescu, A Lopez, S Goldwater
arXiv preprint arXiv:1809.01431, 2018
1782018
Deep convolutional acoustic word embeddings using word-pair side information
H Kamper, W Wang, K Livescu
IEEE ICASSP, 2016
1762016
Unsupervised neural network based feature extraction using weak top-down constraints
H Kamper, M Elsner, A Jansen, S Goldwater
IEEE ICASSP, 2015
1322015
Vector-quantized neural networks for acoustic unit discovery in the ZeroSpeech 2020 challenge
B van Niekerk, L Nortje, H Kamper
arXiv preprint arXiv:2005.09409, 2020
1172020
A segmental framework for fully-unsupervised large-vocabulary speech recognition
H Kamper, A Jansen, S Goldwater
Computer Speech & Language, 2017
1172017
A comparison of neural network methods for unsupervised representation learning on the Zero Resource Speech Challenge
D Renshaw, H Kamper, A Jansen, S Goldwater
Interspeech, 2015
1092015
Participatory research for low-resourced machine translation: A case study in african languages
W Nekoto, V Marivate, T Matsila, T Fasubaa, T Kolawole, T Fagbohungbe, ...
arXiv preprint arXiv:2010.02353, 2020
1052020
Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages
W Nekoto, V Marivate, T Matsila, T Fasubaa, T Kolawole, T Fagbohungbe, ...
EMNLP Findings, 2020
1052020
An embedded segmental k-means model for unsupervised segmentation and clustering of speech
H Kamper, K Livescu, S Goldwater
IEEE ASRU, 719-726, 2017
952017
Unsupervised word segmentation and lexicon discovery using acoustic word embeddings
H Kamper, A Jansen, S Goldwater
IEEE Transactions on Audio, Speech, and Language Processing, 2016
902016
Query-by-Example Search with Discriminative Neural Acoustic Word Embeddings
S Settle, K Levin, H Kamper, K Livescu
arXiv preprint arXiv:1706.03818, 2017
852017
Towards speech-to-text translation without speech recognition
S Bansal, H Kamper, A Lopez, S Goldwater
arXiv preprint arXiv:1702.03856, 2017
702017
Truly unsupervised acoustic word embeddings using weak top-down constraints in encoder-decoder models
H Kamper
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019
652019
Visually grounded learning of keyword prediction from untranscribed speech
H Kamper, S Settle, G Shakhnarovich, K Livescu
arXiv preprint arXiv:1703.08136, 2017
632017
Low-Resource Speech-to-Text Translation
S Bansal, H Kamper, K Livescu, A Lopez, S Goldwater
arXiv preprint arXiv:1803.09164, 2018
572018
Semantic Speech Retrieval With a Visually Grounded Model of Untranscribed Speech.
H Kamper, G Shakhnarovich, K Livescu
IEEE/ACM Transactions on Audio, Speech and Language Processing 27 (1), 89-98, 2019
562019
Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networks
R Eloff, A Nortje, B van Niekerk, A Govender, L Nortje, A Pretorius, ...
arXiv preprint arXiv:1904.07556, 2019
542019
Fully unsupervised small-vocabulary speech recognition using a segmental Bayesian model
H Kamper, A Jansen, S Goldwater
Interspeech, 2015
472015
Masakhane--Machine Translation For Africa
I Orife, J Kreutzer, B Sibanda, D Whitenack, K Siminyu, L Martinus, JT Ali, ...
arXiv preprint arXiv:2003.11529, 2020
402020
Multimodal One-shot Learning of Speech and Images
R Eloff, HA Engelbrecht, H Kamper
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019
382019
Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.
Članci 1–20