Canonical correlation analysis and local fisher discriminant analysis based multi-view acoustic feature reduction for physical load prediction

Kaya, Heysem; Ozkaptan, Tugce; Salah, Albert Ali; Gürgen, Sadik Fikret

doi:10.21437/interspeech.2014-107

Cited by 12 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We performed our experiments on the 6373-sized feature set extracted by the Challenge organizers, which is naturally full of redundant and irrelevant features. Although current state-ofthe-art machine learning methods are able to make reliable predictions in this extremely high-dimensional space, it was shown that they can be assisted by feature selection in paralinguistic tasks as well [23,24]. Therefore we decided to also carry out some kind of feature selection.…”

Section: Feature Selectionmentioning

confidence: 99%

Assessing the degree of nativeness and Parkinson's condition using Gaussian processes and deep rectifier neural networks

et al. 2015

View full text Add to dashboard Cite

The Interspeech 2015 Computational Paralinguistics Challenge includes two regression learning tasks, namely the Parkinson's Condition Sub-Challenge and the Degree of Nativeness Sub-Challenge. We evaluated two state-of-the-art machine learning methods on the tasks, namely Deep Neural Networks (DNN) and Gaussian Processes Regression (GPR). We also experiented with various classifier combination and feature selection methods. For the Degree of Nativeness sub-challenge we obtained a far better Spearman correlation value than the one presented in the baseline paper. As regards the Parkinson's Condition Sub-Challenge, we showed that both DNN and GPR are competitive with the baseline SVM, and that the results can be improved further by combining the classifiers. However, we obtained by far the best results when we applied a speaker clustering method to identify the files that belong to the same speaker.

show abstract

Section: Feature Selectionmentioning

confidence: 99%

Assessing the degree of nativeness and Parkinson's condition using Gaussian processes and deep rectifier neural networks

et al. 2015

View full text Add to dashboard Cite

show abstract

“…Researchers have used different handcrafted acoustic features like Mel-frequency cepstral coefficients (MFCC), prosodic features, Teager energy-based features etc., for neutral vs OBS classification. Various machine learning tools like support vector machine (SVM), hidden Markov model (HMM) and AdaBoost have been used for the classification task [2], [11]- [13]. Some works have used deep neural networks (DNN) for the classification.…”

Section: Introductionmentioning

confidence: 99%

Multi-Task Learning using Frequency-Warped Spectrum for Detecting Out-of-breath Speech

Sahoo¹,

Dandapat²

2022

Preprint

View full text Add to dashboard Cite

This paper presents methods for detecting out-of-breath speech (OBS) under the shortness-of-breath condition due to physical load. It uses constant Q transform (CQT) for warping frequency spectrum non-linearly, which focuses on spectral saliencies of speech signal under the said condition. The existing works using deep neural networks (DNN) have spectrograms or prosodic features as input to detect the OBS speech. Two target labels, neutral and OBS, are commonly used for training DNN models. The labels, however, do not reflect the true exertion level in a speaker. In this work, a transfer-learning approach is proposed for estimating the physical exertion level. An open-source DNN model, which is trained on environmental sounds, is used for the same purpose. A multi-task learning (MTL) framework is applied for jointly learning the binary class labels and the exertion levels. The results show that the spectrogram with non-linear frequency warping performs better than its linear counterparts. Furthermore, with MTL, the classification performance F1-score improves by 3.54% and 12.67% over the single task learning (STL) using CQT-spectrogram and Mel-spectrogram, respectively.

show abstract

A feature selection-based speaker clustering method for paralinguistic tasks

Gosztolya

Tóth

2017

Pattern Anal Applic

View full text Add to dashboard Cite

Canonical correlation analysis and local fisher discriminant analysis based multi-view acoustic feature reduction for physical load prediction

Cited by 12 publications

References 16 publications

Assessing the degree of nativeness and Parkinson's condition using Gaussian processes and deep rectifier neural networks

Assessing the degree of nativeness and Parkinson's condition using Gaussian processes and deep rectifier neural networks

Multi-Task Learning using Frequency-Warped Spectrum for Detecting Out-of-breath Speech

A feature selection-based speaker clustering method for paralinguistic tasks

Contact Info

Product

Resources

About