b'Herman Kamper'

research

∙ 06/01/2023

Towards hate speech detection in low-resource languages: Comparing ASR to acoustic word embeddings on Wolof and Swahili

We consider hate speech detection through keyword spotting on radio broa...

0 Christiaan Jacobs, et al. ∙

research

∙ 05/30/2023

Voice Conversion With Just Nearest Neighbors

Any-to-any voice conversion aims to transform source speech into a targe...

0 Matthew Baas, et al. ∙

research

∙ 05/25/2023

Visually grounded few-shot word acquisition with fewer shots

We propose a visually grounded speech model that acquires new words and ...

0 Leanne Nortje, et al. ∙

research

∙ 05/22/2023

Mitigating Catastrophic Forgetting for Few-Shot Spoken Word Classification Through Meta-Learning

We consider the problem of few-shot spoken word classification in a sett...

0 Ruan van der Merwe, et al. ∙

research

∙ 10/14/2022

TransFusion: Transcribing Speech with Multinomial Diffusion

Diffusion models have shown exceptional scaling properties in the image ...

0 Matthew Baas, et al. ∙

research

∙ 10/12/2022

Towards visually prompted keyword localisation for zero-resource spoken languages

Imagine being able to show a system a visual depiction of a keyword and ...

0 Leanne Nortje, et al. ∙

research

∙ 10/11/2022

GAN You Hear Me? Reclaiming Unconditional Speech Synthesis from Diffusion Models

We propose AudioStyleGAN (ASGAN), a new generative adversarial network (...

0 Matthew Baas, et al. ∙

research

∙ 10/10/2022

YFACC: A Yorùbá speech-image dataset for cross-lingual keyword localisation through visual grounding

Visually grounded speech (VGS) models are trained on images paired with ...

0 Kayode Olaleye, et al. ∙

research

∙ 06/23/2022

A Temporal Extension of Latent Dirichlet Allocation for Unsupervised Acoustic Unit Discovery

Latent Dirichlet allocation (LDA) is widely used for unsupervised topic ...

0 Werner van der Merwe, et al. ∙

research

∙ 02/24/2022

Word Segmentation on Discovered Phone Units with Dynamic Programming and Self-Supervised Scoring

Recent work on unsupervised speech segmentation has used self-supervised...

0 Herman Kamper, et al. ∙

research

∙ 02/02/2022

Keyword localisation in untranscribed speech using visually grounded speech models

Keyword localisation is the task of finding where in a speech utterance ...

0 Kayode Olaleye, et al. ∙

research

∙ 11/04/2021

Towards Learning to Speak and Hear Through Multi-Agent Communication over a Continuous Acoustic Channel

While multi-agent reinforcement learning has been used as an effective m...

0 Kevin Eloff, et al. ∙

research

∙ 11/04/2021

Voice Conversion Can Improve ASR in Very Low-Resource Settings

Voice conversion (VC) has been proposed to improve speech recognition sy...

0 Matthew Baas, et al. ∙

research

∙ 11/03/2021

A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion

The goal of voice conversion is to transform source speech into a target...

0 Benjamin van Niekerk, et al. ∙

research

∙ 08/02/2021

Analyzing Speaker Information in Self-Supervised Models to Improve Zero-Resource Speech Processing

Contrastive predictive coding (CPC) aims to learn representations of spe...

0 Benjamin van Niekerk, et al. ∙

research

∙ 07/03/2021

Mava: a research framework for distributed multi-agent reinforcement learning

Breakthrough advances in reinforcement learning (RL) research have led t...

18 Arnu Pretorius, et al. ∙

research

∙ 06/24/2021

Multilingual transfer of acoustic word embeddings improves when training on languages related to the target zero-resource language

Acoustic word embedding models map variable duration speech segments to ...

0 Christiaan Jacobs, et al. ∙

research

∙ 06/16/2021

Attention-Based Keyword Localisation in Speech using Visual Grounding

Visually grounded speech models learn from images paired with spoken cap...

0 Kayode Olaleye, et al. ∙

research

∙ 05/31/2021

StarGAN-ZSVC: Towards Zero-Shot Voice Conversion in Low-Resource Contexts

Voice conversion is the task of converting a spoken utterance from a sou...

0 Matthew Baas, et al. ∙

research

∙ 03/19/2021

Acoustic word embeddings for zero-resource languages using self-supervised contrastive learning and multilingual adaptation

Acoustic word embeddings (AWEs) are fixed-dimensional representations of...

0 Christiaan Jacobs, et al. ∙

research

∙ 01/27/2021

A phonetic model of non-native spoken word processing

Non-native speakers show difficulties with spoken word processing. Many ...

0 Yevgen Matusevych, et al. ∙

research

∙ 12/14/2020

Towards unsupervised phone and word segmentation using self-supervised vector-quantized neural networks

We investigate segmenting and clustering speech into low-bitrate phone-l...

0 Herman Kamper, et al. ∙

research

∙ 12/14/2020

Towards localisation of keywords in speech using weak supervision

Developments in weakly supervised and self-supervised models could enabl...

0 Kayode Olaleye, et al. ∙

research

∙ 12/14/2020

A comparison of self-supervised speech representations as input features for unsupervised acoustic word embeddings

Many speech processing tasks involve measuring the acoustic similarity b...

0 Lisa van Staden, et al. ∙

research

∙ 12/10/2020

Direct multimodal few-shot learning of speech and images

We propose direct multimodal few-shot models that learn a shared embeddi...

0 Leanne Nortje, et al. ∙

research

∙ 12/03/2020

A Correspondence Variational Autoencoder for Unsupervised Acoustic Word Embeddings

We propose a new unsupervised model for mapping a variable-duration spee...

0 Puyuan Peng, et al. ∙

research

∙ 10/05/2020

Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages

Research in NLP lacks geographic diversity, and the question of how NLP ...

0 Wilhelmina Nekoto, et al. ∙

research

∙ 08/14/2020

Unsupervised vs. transfer learning for multimodal one-shot matching of speech and images

We consider the task of multimodal one-shot speech-image matching. An ag...

0 Leanne Nortje, et al. ∙

research

∙ 08/06/2020

Evaluating computational models of infant phonetic learning across languages

In the first year of life, infants' speech perception becomes attuned to...

0 Yevgen Matusevych, et al. ∙

research

∙ 06/02/2020

Improved acoustic word embeddings for zero-resource languages using multilingual transfer

Acoustic word embeddings are fixed-dimensional representations of variab...

0 Herman Kamper, et al. ∙

research

∙ 05/19/2020

Vector-quantized neural networks for acoustic unit discovery in the ZeroSpeech 2020 challenge

In this paper, we explore vector quantization for acoustic unit discover...

0 Benjamin van Niekerk, et al. ∙

research

∙ 04/03/2020

Analyzing autoencoder-based acoustic word embeddings

Recent studies have introduced methods for learning acoustic word embedd...

0 Yevgen Matusevych, et al. ∙

research

∙ 03/28/2020

Unsupervised feature learning for speech using correspondence and Siamese networks

In zero-resource settings where transcribed speech audio is unavailable,...

0 Petri-Johan Last, et al. ∙

research

∙ 03/13/2020

Masakhane – Machine Translation For Africa

Africa has over 2000 languages. Despite this, African languages account ...

0 Iroro Orife, et al. ∙

research

∙ 02/06/2020

Multilingual acoustic word embedding models for processing zero-resource languages

Acoustic word embeddings are fixed-dimensional representations of variab...

0 Herman Kamper, et al. ∙

research

∙ 12/11/2019

Deep motion estimation for parallel inter-frame prediction in video compression

Standard video codecs rely on optical flow to guide inter-frame predicti...

0 André Nortje, et al. ∙

research

∙ 12/11/2019

BINet: a binary inpainting network for deep patch-based image compression

Recent deep learning models outperform standard lossy image compression ...

22 André Nortje, et al. ∙

research

∙ 10/13/2019

If dropout limits trainable depth, does critical initialisation still matter? A large-scale statistical analysis on ReLU networks

Recent work in signal propagation theory has shown that dropout limits t...

0 Arnu Pretorius, et al. ∙

research

∙ 10/12/2019

On the expected behaviour of noise regularised deep neural networks as Gaussian processes

Recent work has established the equivalence between deep neural networks...

22 Arnu Pretorius, et al. ∙

research

∙ 08/29/2019

Classifying topics in speech when all you have is crummy translations

Given a large amount of unannotated speech in a language with few resour...

0 Sameer Bansal, et al. ∙

research

∙ 04/24/2019

On the Contributions of Visual and Textual Supervision in Low-resource Semantic Speech Retrieval

Recent work has shown that speech paired with images can be used to lear...

0 Ankita Pasad, et al. ∙

research

∙ 04/16/2019

Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networks

For our submission to the ZeroSpeech 2019 challenge, we apply discrete l...

0 Ryan Eloff, et al. ∙

research

∙ 04/15/2019

Semantic query-by-example speech search using visual grounding

A number of recent studies have started to investigate how speech system...

0 Herman Kamper, et al. ∙

research

∙ 11/14/2018

Almost Zero-Resource ASR-free Keyword Spotting using Multilingual Bottleneck Features and Correspondence Autoencoders

We compare features for dynamic time warping based keyword spotting in a...

0 Raghav Menon, et al. ∙

research

∙ 11/09/2018

Multimodal One-Shot Learning of Speech and Images

Imagine a robot is shown new concepts visually together with spoken tags...

0 Ryan Eloff, et al. ∙

research

∙ 11/09/2018

Multilingual and Unsupervised Subword Modeling for Zero-Resource Languages

Unsupervised subword modeling aims to learn low-level representations of...

0 Enno Hermann, et al. ∙

research

∙ 11/01/2018

Truly unsupervised acoustic word embeddings using weak top-down constraints in encoder-decoder models

We investigate unsupervised models that can map a variable-duration spee...

0 Herman Kamper, et al. ∙

research

∙ 11/01/2018

Critical initialisation for deep signal propagation in noisy rectifier neural networks

Stochastic regularisation is an important weapon in the arsenal of a dee...

6 Arnu Pretorius, et al. ∙

research

∙ 09/05/2018

Pre-training on high-resource speech recognition improves low-resource speech-to-text translation

We present a simple approach to improve direct speech-to-text translatio...

0 Sameer Bansal, et al. ∙

research

∙ 07/23/2018

ASR-free CNN-DTW keyword spotting using multilingual bottleneck features for almost zero-resource languages

We consider multilingual bottleneck features (BNFs) for nearly zero-reso...

0 Raghav Menon, et al. ∙

Herman Kamper

Featured Co-authors