111 citations · 462 across the 65 of their papers we have counts for
12 papers · 2 filters
Towards localisation of keywords in speech using weak supervision
Kayode Olaleye, Benjamin van Niekerk, Herman Kamper
Developments in weakly supervised and self-supervised models could enable speech technology in low-resource settings where full transcriptions are not available. We consider whethe…
A comparison of self-supervised speech representations as input features for unsupervised acoustic word embeddings
Lisa van Staden, Herman Kamper
Many speech processing tasks involve measuring the acoustic similarity between speech segments. Acoustic word embeddings (AWE) allow for efficient comparisons by mapping speech seg…
Towards unsupervised phone and word segmentation using self-supervised vector-quantized neural networks
Herman Kamper, Benjamin van Niekerk
We investigate segmenting and clustering speech into low-bitrate phone-like sequences without supervision. We specifically constrain pretrained self-supervised vector-quantized (VQ…
Direct multimodal few-shot learning of speech and images
Leanne Nortje, Herman Kamper
We propose direct multimodal few-shot models that learn a shared embedding space of spoken words and images from only a few paired examples. Imagine an agent is shown an image alon…
Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages
Wilhelmina Nekoto, Vukosi Marivate, Tshinondiwa Matsila +45
Research in NLP lacks geographic diversity, and the question of how NLP can be scaled to low-resourced languages has not yet been adequately solved. "Low-resourced"-ness is a compl…
Unsupervised vs. transfer learning for multimodal one-shot matching of speech and images
Leanne Nortje, Herman Kamper
We consider the task of multimodal one-shot speech-image matching. An agent is shown a picture along with a spoken word describing the object in the picture, e.g. cookie, broccoli…
Evaluating computational models of infant phonetic learning across languages
Yevgen Matusevych, Thomas Schatz, Herman Kamper +2
In the first year of life, infants' speech perception becomes attuned to the sounds of their native language. Many accounts of this early phonetic learning exist, but computational…
Improved acoustic word embeddings for zero-resource languages using multilingual transfer
Herman Kamper, Yevgen Matusevych, Sharon Goldwater
Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. Such embeddings can form the basis for speech search, indexing and discovery syst…
Analyzing autoencoder-based acoustic word embeddings
Yevgen Matusevych, Herman Kamper, Sharon Goldwater
Recent studies have introduced methods for learning acoustic word embeddings (AWEs)---fixed-size vector representations of words which encode their acoustic features. Despite the w…
Unsupervised feature learning for speech using correspondence and Siamese networks
Petri-Johan Last, Herman A. Engelbrecht, Herman Kamper
In zero-resource settings where transcribed speech audio is unavailable, unsupervised feature learning is essential for downstream speech processing tasks. Here we compare two rece…
Masakhane -- Machine Translation For Africa
Iroro Orife, Julia Kreutzer, Blessing Sibanda +22
Africa has over 2000 languages. Despite this, African languages account for a small portion of available resources and publications in Natural Language Processing (NLP). This is du…
Multilingual acoustic word embedding models for processing zero-resource languages
Herman Kamper, Yevgen Matusevych, Sharon Goldwater
Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. In settings where unlabelled speech is the only available resource, such embeddin…