Coding and Decoding Speech using a Biologically Inspired Coding System

Pahar, Madhurananda; Smith, Leslie S.

doi:10.1109/ssci47803.2020.9308328

Cited by 17 publications

(12 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MFCCs have been very effective in speech processing [ 35 ], but also in discriminating dry and wet coughs [ 36 ], and recently in characterising COVID-19 audio [ 37 ]. Linearly-spaced log filterbank energies have proved useful in several biomedical applications, including cough audio classification [ 24 , 25 , 38 ].…”

Section: Primary Feature Extractionmentioning

confidence: 99%

COVID-19 detection in cough, breath and speech using deep transfer learning and bottleneck features

Pahar

Klopper

Warren

et al. 2022

Computers in Biology and Medicine

Self Cite

View full text Add to dashboard Cite

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 and speech. This type of screening is non-contact, does not require specialist medical expertise or laboratory facilities and can be deployed on inexpensive consumer hardware such as a smartphone. We use datasets that contain cough, sneeze, speech and other noises, but do not contain COVID-19 labels, to pre-train three deep neural networks: a CNN, an LSTM and a Resnet50. These pre-trained networks are subsequently either fine-tuned using smaller datasets of coughing with COVID-19 labels in the process of transfer learning, or are used as bottleneck feature extractors. Results show that a Resnet50 classifier trained by this transfer learning process delivers optimal or near-optimal performance across all datasets achieving areas under the receiver operating characteristic (ROC AUC) of 0.98, 0.94 and 0.92 respectively for all three sound classes: coughs, breaths and speech. This indicates that coughs carry the strongest COVID-19 signature, followed by breath and speech. Our results also show that applying transfer learning and extracting bottleneck features using the larger datasets without COVID-19 labels led not only to improved performance, but also to a marked reduction in the standard deviation of the classifier AUCs measured over the outer folds during nested cross-validation, indicating better generalisation. We conclude that deep transfer learning and bottleneck feature extraction can improve COVID-19 cough, breath and speech audio classification, yielding automatic COVID-19 detection with a better and more consistent overall performance.

show abstract

Section: Primary Feature Extractionmentioning

confidence: 99%

COVID-19 detection in cough, breath and speech using deep transfer learning and bottleneck features

Pahar

Klopper

Warren

et al. 2022

Computers in Biology and Medicine

Self Cite

View full text Add to dashboard Cite

show abstract

“…In ongoing work, we are attempting to optimise some of the Resnet50 metaparameters and also to incorporate audio [26] along with accelerometer measurements with a view to further improvement on cough detection results.…”

Section: Discussionmentioning

confidence: 99%

Deep Neural Network Based Cough Detection Using Bed-Mounted Accelerometer Measurements

Pahar

Miranda

Diacon

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

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 accelerometer sensors, and sidesteps privacy concerns encountered when using audio for cough detection. For our experiments, we have compiled a manually-annotated dataset containing the acceleration signals of approximately 6000 cough and 68000 non-cough events from 14 adult male patients in a tuberculosis clinic. As classifiers, we have considered convolutional neural networks (CNN), long-short-term-memory (LSTM) networks, and a residual neural network (Resnet50). We find that all classifiers are able to distinguish between the acceleration signals due to coughing and those due to other activities including sneezing, throat-clearing and movement in the bed with high accuracy. The Resnet50 performs the best, achieving an area under the ROC curve (AUC) exceeding 0.98 in cross-validation experiments. We conclude that high-accuracy cough monitoring based only on measurements from the accelerometer in a consumer smartphone is possible. Since the need to gather audio is avoided and therefore privacy is inherently protected, and since the accelerometer is attached to the bed and not worn, this form of monitoring may represent a more convenient and readily accepted method of long-term patient cough monitoring.

show abstract

“…We want our system to use specific musical features from different sub-bands of our audio files to generate a new beat out of our samples from our database. To do this, we will take inspiration from work presented in [6] where a speech coding system is proposed using biological processes in the auditory nervous system (AN). In this work, speech signals are able represented using solely using the zero crossing metric from different sub-bands (i.e.…”

Section: Preprocessing and Mapping Audio Signals To Qubitsmentioning

confidence: 99%

QuiKo: A Quantum Beat Generation Application

Oshiro¹

2022

Preprint

View full text Add to dashboard Cite

Coding and Decoding Speech using a Biologically Inspired Coding System

Cited by 17 publications

References 15 publications

COVID-19 detection in cough, breath and speech using deep transfer learning and bottleneck features

COVID-19 detection in cough, breath and speech using deep transfer learning and bottleneck features

Deep Neural Network Based Cough Detection Using Bed-Mounted Accelerometer Measurements

QuiKo: A Quantum Beat Generation Application

Contact Info

Product

Resources

About