10 citations · 16 across the 9 of their papers we have counts for
10 papers
Analyzing and Improving Speaker Similarity Assessment for Speech Synthesis
Marc-André Carbonneau, Benjamin van Niekerk, Hugo Seuté +3
Modeling voice identity is challenging due to its multifaceted nature. In generative speech systems, identity is often assessed using automatic speaker verification (ASV) embedding…
LinearVC: Linear transformations of self-supervised features through the lens of voice conversion
Herman Kamper, Benjamin van Niekerk, Julian Zaïdi +1
We introduce LinearVC, a simple voice conversion method that sheds light on the structure of self-supervised representations. First, we show that simple linear transformations of s…
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…
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…
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…
Vector-quantized neural networks for acoustic unit discovery in the ZeroSpeech 2020 challenge
Benjamin van Niekerk, Leanne Nortje, Herman Kamper
In this paper, we explore vector quantization for acoustic unit discovery. Leveraging unlabelled data, we aim to learn discrete representations of speech that separate phonetic con…
Online Constrained Model-based Reinforcement Learning
Benjamin van Niekerk, Andreas Damianou, Benjamin Rosman
Applying reinforcement learning to robotic systems poses a number of challenging problems. A key requirement is the ability to handle continuous state and action spaces while remai…
If dropout limits trainable depth, does critical initialisation still matter? A large-scale statistical analysis on ReLU networks
Arnu Pretorius, Elan van Biljon, Benjamin van Niekerk +6
Recent work in signal propagation theory has shown that dropout limits the depth to which information can propagate through a neural network. In this paper, we investigate the effe…
Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networks
Ryan Eloff, André Nortje, Benjamin van Niekerk +7
For our submission to the ZeroSpeech 2019 challenge, we apply discrete latent-variable neural networks to unlabelled speech and use the discovered units for speech synthesis. Unsup…
Will it Blend? Composing Value Functions in Reinforcement Learning
Benjamin van Niekerk, Steven James, Adam Earle +1
An important property for lifelong-learning agents is the ability to combine existing skills to solve unseen tasks. In general, however, it is unclear how to compose skills in a pr…