Voice data mining for laryngeal pathology assessment

Hemmerling, Daria; Skalski, Andrzej; Gajda, Janusz

doi:10.1016/j.compbiomed.2015.07.026

Cited by 40 publications

(36 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From these reasons, works such as [17, [18,39], SVD -Saarbruecken Voice Database [62,44,2], AVPD -Arabic Voice Pathology Database [41,44], KM -K-means [23], RF -Random Forests [11], GMM -Gaussian Mixture Models [50], SVM -Support Vector Machines [24], NB -Naive Bayes [45], ELM -Extreme Learning Machine [30], and ANN -Artificial Neural Networks [53]. 26,44,2] focused on using signal processing techniques (to quantify vocal-manifestations of the pathology under focus) and machine learning algorithms (to automate the process of voice pathology detection) to build a system capable of accurate discrimination of healthy and pathological voices. In Table 1, we summarize recent (2015 -now) related works focused on the objective voice pathology detection.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Towards robust voice pathology detection

Harár

Galáž

Alonso-Hernández

et al. 2018

Neural Comput & Applic

View full text Add to dashboard Cite

Automatic objective non-invasive detection of pathological voice based on computerized analysis of acoustic signals can play an important role in early diagnosis, progression tracking and even effective treatment of pathological voices. In search towards such a robust voice pathology detection system we investigated 3 distinct classifiers within supervised learning and anomaly detection paradigms. We conducted a set of experiments using a variety of input data such as raw waveforms, spectrograms, mel-frequency cepstral coefficients (MFCC) and conventional acoustic (dysphonic) features (AF). In comparison with previously published works, this article is the first to utilize combination of 4 different databases comprising normophonic and pathological recordings of sustained phonation of the vowel /a/ unrestricted to a subset of vocal pathologies. Furthermore, to our best knowledge, this article is the first to explore gradient boosted trees and deep learning for this application. The following best classification performances measured by F1 score on dedicated test set were achieved: XGBoost (0.733) using AF and MFCC, DenseNet (0.621) using MFCC, and Isolation Forest (0.610) using AF. Even though these results are of exploratory character, conducted experiments do show promising potential of gradient boosting and deep learning methods to robustly detect voice pathologies.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Some researchers also analyzed a combination of the vowels, e.g. [36,17,26], etc. From the voice pathologies point of view, most researchers restricted the dataset to a limited set of pathologies [7,43,14,25,51,44,5,3,4,2].…”

Section: Introductionmentioning

confidence: 99%

Towards robust voice pathology detection

Harár

Galáž

Alonso-Hernández

et al. 2018

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…Our future work will build on current experiment, but we will limit the number of pathologies only to those having the most samples as in [2], [8]- [10] and we will train separate models for males and females as in [15]. We will investigate whether training with combination of vowels /a/, /i/ and /u/ help to improve the accuracy as in [7], [12], [15]. Also we will incorporate the data from other publicly available datasets and introduce permutation test to validate if the model learned to recognize meaningful features or just overfits on noise or remembers the samples.…”

Section: Resultsmentioning

confidence: 99%

Voice Pathology Detection Using Deep Learning: a Preliminary Study

Harár

Alonso-Hernandezy

Mekyska

et al. 2017

2017 International Conference and Workshop on Bioinspired Intelligence (IWOBI)

View full text Add to dashboard Cite

This paper describes a preliminary investigation of Voice Pathology Detection using Deep Neural Networks (DNN). We used voice recordings of sustained vowel /a/ produced at normal pitch from German corpus Saarbruecken Voice Database (SVD). This corpus contains voice recordings and electroglottograph signals of more than 2 000 speakers. The idea behind this experiment is the use of convolutional layers in combination with recurrent Long-Short-Term-Memory (LSTM) layers on raw audio signal. Each recording was split into 64 ms Hamming windowed segments with 30 ms overlap. Our trained model achieved 71.36 % accuracy with 65.04 % sensitivity and 77.67 % specificity on 206 validation files and 68.08 % accuracy with 66.75 % sensitivity and 77.89 % specificity on 874 testing files. This is a promising result in favor of this approach because it is comparable to similar previously published experiment that used different methodology. Further investigation is needed to achieve the state-of-the-art results.

show abstract

“…Because this is a new database, little research has been done using this database, which are listed in Table II. From the literatures, we can see that Saarbruecken Voice Database appears more challenging while more trust-worthy for experiments. Some experiments use small amount of data and achieved almost 100% accuracy using statistical methods [6,8,9]. This is questionable compared to [10] using GMM-HMM which achieves 67.00% accuracy when the data amount is large.…”

Section: Convolutional Neural Network For Pathological Voice Detectionmentioning

confidence: 99%

Convolutional Neural Networks for Pathological Voice Detection

Soraghan

Lowit

et al. 2018

2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

View full text Add to dashboard Cite

Acoustic analysis using signal processing tools can be used to extract voice features to distinguish whether a voice is pathological or healthy. The proposed work uses spectrogram of voice recordings from a voice database as the input to a Convolutional Neural Network (CNN) for automatic feature extraction and classification of disordered and normal voice. The novel classifier achieved 88.5%, 66.2% and 77.0% accuracy on training, validation and testing data set respectively on 482 normal and 482 organic dysphonia speech files. It reveals that the proposed novel algorithm on the Saarbruecken Voice Database can effectively been used for screening pathological voice recordings.

show abstract

Voice data mining for laryngeal pathology assessment

Cited by 40 publications

References 29 publications

Towards robust voice pathology detection

Towards robust voice pathology detection

Voice Pathology Detection Using Deep Learning: a Preliminary Study

Convolutional Neural Networks for Pathological Voice Detection

Contact Info

Product

Resources

About