111 citations · 462 across the 65 of their papers we have counts for
11 papers · 1 filter
Towards Learning to Speak and Hear Through Multi-Agent Communication over a Continuous Acoustic Channel
Kevin Eloff, Okko Räsänen, Herman A. Engelbrecht +2
Multi-agent reinforcement learning has been used as an effective means to study emergent communication between agents, yet little focus has been given to continuous acoustic commun…
Voice Conversion Can Improve ASR in Very Low-Resource Settings
Matthew Baas, Herman Kamper
Voice conversion (VC) could be used to improve speech recognition systems in low-resource languages by using it to augment limited training data. However, VC has not been widely us…
A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion
Benjamin van Niekerk, Marc-André Carbonneau, Julian Zaïdi +3
The goal of voice conversion is to transform source speech into a target voice, keeping the content unchanged. In this paper, we focus on self-supervised representation learning fo…
Feature learning for efficient ASR-free keyword spotting in low-resource languages
Ewald van der Westhuizen, Herman Kamper, Raghav Menon +2
We consider feature learning for efficient keyword spotting that can be applied in severely under-resourced settings. The objective is to support humanitarian relief programmes by…
Analyzing Speaker Information in Self-Supervised Models to Improve Zero-Resource Speech Processing
Benjamin van Niekerk, Leanne Nortje, Matthew Baas +1
Contrastive predictive coding (CPC) aims to learn representations of speech by distinguishing future observations from a set of negative examples. Previous work has shown that line…
Mava: a research library for distributed multi-agent reinforcement learning in JAX
Ruan de Kock, Omayma Mahjoub, Sasha Abramowitz +5
Multi-agent reinforcement learning (MARL) research is inherently computationally expensive and it is often difficult to obtain a sufficient number of experiment samples to test hyp…
Multilingual transfer of acoustic word embeddings improves when training on languages related to the target zero-resource language
Christiaan Jacobs, Herman Kamper
Acoustic word embedding models map variable duration speech segments to fixed dimensional vectors, enabling efficient speech search and discovery. Previous work explored how embedd…
Attention-Based Keyword Localisation in Speech using Visual Grounding
Kayode Olaleye, Herman Kamper
Visually grounded speech models learn from images paired with spoken captions. By tagging images with soft text labels using a trained visual classifier with a fixed vocabulary, pr…
StarGAN-ZSVC: Towards Zero-Shot Voice Conversion in Low-Resource Contexts
Matthew Baas, Herman Kamper
Voice conversion is the task of converting a spoken utterance from a source speaker so that it appears to be said by a different target speaker while retaining the linguistic conte…
Acoustic word embeddings for zero-resource languages using self-supervised contrastive learning and multilingual adaptation
Christiaan Jacobs, Yevgen Matusevych, Herman Kamper
Acoustic word embeddings (AWEs) are fixed-dimensional representations of variable-length speech segments. For zero-resource languages where labelled data is not available, one AWE…
A phonetic model of non-native spoken word processing
Yevgen Matusevych, Herman Kamper, Thomas Schatz +2
Non-native speakers show difficulties with spoken word processing. Many studies attribute these difficulties to imprecise phonological encoding of words in the lexical memory. We t…