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

Grósz, Tamás; Busa-Fekete, Róbert; Gosztolya, Gábor; Tóth, László

doi:10.21437/interspeech.2015-195

Cited by 23 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used our custom DNN implementation for GPU, which achieved out- standing results on several datasets (e.g. [24,25,26,27,28]). We used 40 mel filter bank energies as features along with their first and second order derivatives.…”

Section: Methodsmentioning

confidence: 99%

GMM-Free Flat Start Sequence-Discriminative DNN Training

Gosztolya¹,

Grósz²,

Tóth³

2016

Interspeech 2016

Self Cite

View full text Add to dashboard Cite

Recently, attempts have been made to remove Gaussian mixture models (GMM) from the training process of deep neural network-based hidden Markov models (HMM/DNN). For the GMM-free training of a HMM/DNN hybrid we have to solve two problems, namely the initial alignment of the frame-level state labels and the creation of context-dependent states. Although flat-start training via iteratively realigning and retraining the DNN using a frame-level error function is viable, it is quite cumbersome. Here, we propose to use a sequencediscriminative training criterion for flat start. While sequencediscriminative training is routinely applied only in the final phase of model training, we show that with proper caution it is also suitable for getting an alignment of context-independent DNN models. For the construction of tied states we apply a recently proposed KL-divergence-based state clustering method, hence our whole training process is GMM-free. In the experimental evaluation we found that the sequence-discriminative flat start training method is not only significantly faster than the straightforward approach of iterative retraining and realignment, but the word error rates attained are slightly better as well.

show abstract

Section: Methodsmentioning

confidence: 99%

GMM-Free Flat Start Sequence-Discriminative DNN Training

Gosztolya¹,

Grósz²,

Tóth³

2016

Interspeech 2016

Self Cite

View full text Add to dashboard Cite

show abstract

“…Because of this, we have dedicated significant effort to this task. One important lesson from earlier -similar -voice classification challenges was the benefit of combining various models; winners of many of these challenges using a method of ensembling [2,3,4,5,6], often times late fusion. Another guiding principle was the utility of classical machine learning models, particularly in scenarios where the amount of labeled training data is limited.…”

Section: Introductionmentioning

confidence: 99%

Detecting COVID-19 from Audio Recording of Coughs Using Random Forests and Support Vector Machines

Södergren¹,

Nodeh²,

Chhipa³

et al. 2021

Interspeech 2021

View full text Add to dashboard Cite

The detection of COVID-19 is and will remain in the foreseeable future a crucial challenge, making the development of tools for the task important. One possible approach, on the confines of speech and audio processing, is detecting potential COVID-19 cases based on cough sounds. We propose a simple, yet robust method based on the well-known ComParE 2016 feature set, and two classical machine learning models, namely Random Forests, and Support Vector Machines (SVMs). Furthermore, we combine the two methods, by calculating the weighted average of their predictions. Our results in the DiCOVA challenge show that this simple approach leads to a robust solution while producing competitive results. Based on the Area Under the Receiver Operating Characteristic Curve (AUC ROC) score, both classical machine learning methods we applied markedly outperform the baseline provided by the challenge organisers. Moreover, their combination attains an AUC ROC score of 85.21, positioning us at fourth place on the leaderboard (where the second team attained a similar, 85.43 score). Here, we would describe this system in more detail, and analyse the resulting models, drawing conclusions, and determining future work directions.

show abstract

“…Methods such as the i-vector Approach, the Fisher vector, neural networks, among others, are being increasingly used by researchers to address paralinguistic issues. This can be seen in studies like diagnosing neurodegenerative diseases using the speech of the patients [1,2,3]; the discrimination of crying sounds and heartbeats [4]; or the estimation of the sincerity of apologies [5]. These studies aim to distinguish the latent patterns existing within the speech of a subject and not the content of it.…”

Section: Introductionmentioning

confidence: 99%

They are wearing a mask! Identification of Subjects Wearing a Surgical Mask from their Speech by means of x-vectors and Fisher Vectors

Egas-López

2020

Preprint

View full text Add to dashboard Cite

Challenges based on Computational Paralinguistics in the IN-TERSPEECH Conference have always had a good reception among the attendees, owing to its competitive academic and research demands. This year, the INTERSPEECH 2020 Computational Paralinguistics Challenge offers three different problems; here, the Mask Sub-Challenge is of specific interest. This challenge involves the classification of speech recorded from subjects while wearing a surgical mask. In this study, to address the above mentioned problem we employ two different types of feature extraction methods. The x-vectors embeddings, which is the current state-of-the-art approach for Speaker Recognition; and the Fisher Vector (FV), that is a method originally intended for Image Recognition, but here we utilize it to discriminate utterances. These approaches employ distinct frame-level representations: MFCC and PLP. Using Support Vector Machines (SVM) as the classifier, we perform a technical comparison between the performances of the FV encodings and the x-vector embeddings for this particular classification task. We find that the Fisher vector encodings provide better representations of the utterances than the x-vectors do for this specific dataset. Moreover, we show that a fusion of our best configurations outperforms all the baseline scores of the Mask Sub-Challenge.

show abstract

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

Cited by 23 publications

References 26 publications

GMM-Free Flat Start Sequence-Discriminative DNN Training

GMM-Free Flat Start Sequence-Discriminative DNN Training

Detecting COVID-19 from Audio Recording of Coughs Using Random Forests and Support Vector Machines

They are wearing a mask! Identification of Subjects Wearing a Surgical Mask from their Speech by means of x-vectors and Fisher Vectors

Contact Info

Product

Resources

About