English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Prior studies in the automatic classification of voice quality have mainlystudied the use of the acoustic speech signal as input. Recently, a few studieshave been carried out by jointly using both speech and neck surfaceaccelerometer (NSA) signals as inputs, and by extracting MFCCs and glottalsource features. This study examines simultaneously-recorded speech and NSAsignals in the classification of voice quality (breathy, modal, and pressed)using features derived from three self-supervised pre-trained models(wav2vec2-BASE, wav2vec2-LARGE, and HuBERT) and using a SVM as well as CNNs asclassifiers. Furthermore, the effectiveness of the pre-trained models iscompared in feature extraction between glottal source waveforms and raw signalwaveforms for both speech and NSA inputs. Using two signal processing methods(quasi-closed phase (QCP) glottal inverse filtering and zero frequencyfiltering (ZFF)), glottal source waveforms are estimated from both speech andNSA signals. The study has three main goals: (1) to study whether featuresderived from pre-trained models improve classification accuracy compared toconventional features (spectrogram, mel-spectrogram, MFCCs, i-vector, andx-vector), (2) to investigate which of the two modalities (speech vs. NSA) ismore effective in the classification task with pre-trained model-basedfeatures, and (3) to evaluate whether the deep learning-based CNN classifiercan enhance the classification accuracy in comparison to the SVM classifier.The results revealed that the use of the NSA input showed better classificationperformance compared to the speech signal. Between the features, thepre-trained model-based features showed better classification accuracies, bothfor speech and NSA inputs compared to the conventional features. It was alsofound that the HuBERT features performed better than the wav2vec2-BASE andwav2vec2-LARGE features.

Investigation of Self-supervised Pre-trained Models for Classification of Voice Quality from Speech and Neck Surface Accelerometer Signals