299 citations · 646 across the 28 of their papers we have counts for
30 papers
From Birdsong to Rumbles: Classifying Elephant Calls with Out-of-Species Embeddings
Christiaan M. Geldenhuys, Thomas R. Niesler
We show that pretrained acoustic embeddings classify elephant vocalisations at a level approaching that of end-to-end supervised neural networks, without any fine-tuning of the emb…
Low-resource keyword spotting using contrastively trained transformer acoustic word embeddings
Julian Herreilers, Christiaan Jacobs, Thomas Niesler
We introduce a new approach, the ContrastiveTransformer, that produces acoustic word embeddings (AWEs) for the purpose of very low-resource keyword spotting. The ContrastiveTransfo…
Fine-Tuned Self-Supervised Speech Representations for Language Diarization in Multilingual Code-Switched Speech
Geoffrey Frost, Emily Morris, Joshua Jansen van Vüren +1
Annotating a multilingual code-switched corpus is a painstaking process requiring specialist linguistic expertise. This is partly due to the large number of language combinations t…
TB or not TB? Acoustic cough analysis for tuberculosis classification
Geoffrey Frost, Grant Theron, Thomas Niesler
In this work, we explore recurrent neural network architectures for tuberculosis (TB) cough classification. In contrast to previous unsuccessful attempts to implement deep architec…
Automatic Tuberculosis and COVID-19 cough classification using deep learning
Madhurananda Pahar, Marisa Klopper, Byron Reeve +4
We present a deep learning based automatic cough classifier which can discriminate tuberculosis (TB) coughs from COVID-19 coughs and healthy coughs. Both TB and COVID-19 are respir…
Accelerometer-based Bed Occupancy Detection for Automatic, Non-invasive Long-term Cough Monitoring
Madhurananda Pahar, Igor Miranda, Andreas Diacon +1
We present a new machine learning based bed-occupancy detection system that uses the accelerometer signal captured by a bed-attached consumer smartphone. Automatic bed-occupancy de…
Mathematical Content Browsing for Print-Disabled Readers Based on Virtual-World Exploration and Audio-Visual Sensory substitution
Rynhardt Kruger, Febe de Wet, Thomas Niesler
Documents containing mathematical content remain largely inaccessible to blind and visually impaired readers because they are predominantly published as untagged PDF which does not…
Wake-Cough: cough spotting and cougher identification for personalised long-term cough monitoring
Madhurananda Pahar, Marisa Klopper, Byron Reeve +4
We present `wake-cough', an application of wake-word spotting to coughs using a Resnet50 and the identification of coughers using i-vectors, for the purpose of a long-term, persona…
Automatic non-invasive Cough Detection based on Accelerometer and Audio Signals
Madhurananda Pahar, Igor Miranda, Andreas Diacon +1
We present an automatic non-invasive way of detecting cough events based on both accelerometer and audio signals. The acceleration signals are captured by a smartphone firmly attac…
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…
Multilingual training set selection for ASR in under-resourced Malian languages
Ewald van der Westhuizen, Trideba Padhi, Thomas Niesler
We present first speech recognition systems for the two severely under-resourced Malian languages Bambara and Maasina Fulfulde. These systems will be used by the United Nations as…
COVID-19 Detection in Cough, Breath and Speech using Deep Transfer Learning and Bottleneck Features
Madhurananda Pahar, Marisa Klopper, Robin Warren +1
We present an experimental investigation into the effectiveness of transfer learning and bottleneck feature extraction in detecting COVID-19 from audio recordings of cough, breath…
A Hybrid CNN-BiLSTM Voice Activity Detector
Nicholas Wilkinson, Thomas Niesler
This paper presents a new hybrid architecture for voice activity detection (VAD) incorporating both convolutional neural network (CNN) and bidirectional long short-term memory (BiL…
Automatic Cough Classification for Tuberculosis Screening in a Real-World Environment
Madhurananda Pahar, Marisa Klopper, Byron Reeve +3
Objective: The automatic discrimination between the coughing sounds produced by patients with tuberculosis (TB) and those produced by patients with other lung ailments. Approach: W…
Deep Neural Network based Cough Detection using Bed-mounted Accelerometer Measurements
Madhurananda Pahar, Igor Miranda, Andreas Diacon +1
We have performed cough detection based on measurements from an accelerometer attached to the patient's bed. This form of monitoring is less intrusive than body-attached accelerome…
COVID-19 Cough Classification using Machine Learning and Global Smartphone Recordings
Madhurananda Pahar, Marisa Klopper, Robin Warren +1
We present a machine learning based COVID-19 cough classifier which can discriminate COVID-19 positive coughs from both COVID-19 negative and healthy coughs recorded on a smartphon…
Multilingual Bottleneck Features for Improving ASR Performance of Code-Switched Speech in Under-Resourced Languages
Trideba Padhi, Astik Biswas, Febe De Wet +2
In this work, we explore the benefits of using multilingual bottleneck features (mBNF) in acoustic modelling for the automatic speech recognition of code-switched (CS) speech in Af…
Semi-supervised acoustic modelling for five-lingual code-switched ASR using automatically-segmented soap opera speech
N. Wilkinson, A. Biswas, E. Yılmaz +3
This paper considers the impact of automatic segmentation on the fully-automatic, semi-supervised training of automatic speech recognition (ASR) systems for five-lingual code-switc…
Semi-supervised acoustic and language model training for English-isiZulu code-switched speech recognition
A. Biswas, F. de Wet, E. van der Westhuizen +1
We present an analysis of semi-supervised acoustic and language model training for English-isiZulu code-switched ASR using soap opera speech. Approximately 11 hours of untranscribe…
Semi-supervised Development of ASR Systems for Multilingual Code-switched Speech in Under-resourced Languages
Astik Biswas, Emre Yılmaz, Febe de Wet +2
This paper reports on the semi-supervised development of acoustic and language models for under-resourced, code-switched speech in five South African languages. Two approaches are…
Improved low-resource Somali speech recognition by semi-supervised acoustic and language model training
Astik Biswas, Raghav Menon, Ewald van der Westhuizen +1
We present improvements in automatic speech recognition (ASR) for Somali, a currently extremely under-resourced language. This forms part of a continuing United Nations (UN) effort…
Semi-supervised acoustic model training for five-lingual code-switched ASR
Astik Biswas, Emre Yılmaz, Febe de Wet +2
This paper presents recent progress in the acoustic modelling of under-resourced code-switched (CS) speech in multiple South African languages. We consider two approaches. The firs…
Direction of Arrival Estimation of Wide-band Signals with Planar Microphone Arrays
Rudolf Byker, Thomas Niesler
An approach to the estimation of the Direction of Arrival (DOA) of wide-band signals with a planar microphone array is presented. Our algorithm estimates an unambiguous DOA using a…
Feature exploration for almost zero-resource ASR-free keyword spotting using a multilingual bottleneck extractor and correspondence autoencoders
Raghav Menon, Herman Kamper, Ewald van der Westhuizen +2
We compare features for dynamic time warping (DTW) when used to bootstrap keyword spotting (KWS) in an almost zero-resource setting. Such quickly-deployable systems aim to support…