Phonet: A Tool Based on Gated Recurrent Neural Networks to Extract Phonological Posteriors from Speech

Vásquez-Correa, Juan Camilo; Klumpp, Philipp; Orozco-Arroyave, Juan Rafael; Nöth, Elmar

doi:10.21437/interspeech.2019-1405

Cited by 27 publications

(28 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…AF space: There are different ways to represent phonemes as articulatory features such as binary features [26] or multivalued features [27]. In this work, we conducted studies with binary features and multi-valued AF representations: (a) AF binary : We used Phonet toolkit [28], which consists of 18 recurrent neural network-based binary AF classifiers trained on 17 hours of clean FM podcasts in Mexican Spanish. We extracted 18 AF binary probability vectors and used them as the posterior feature, i.e.…”

Section: B Posterior Feature Estimatorsmentioning

confidence: 99%

“…In the Phonet toolkit 1 [28], these AFs are modeled by 18 off-the-shelf recurrent neural network (RNN) based binary classifiers, i.e. D = 18 × 2.…”

Section: A Phonetic Posterior Feature Representationsmentioning

confidence: 99%

“…The RNN classifiers have been trained on 17 hours of clean FM podcasts Mexican Spanish with a cost function based on cross entropy. For more details, related to the mapping between Spanish phones and the AFs and training of RNNs, the reader is referred to [28].…”

Section: A Phonetic Posterior Feature Representationsmentioning

confidence: 99%

See 2 more Smart Citations

Utterance Verification-Based Dysarthric Speech Intelligibility Assessment Using Phonetic Posterior Features

Fritsch

Magimai-Doss

2021

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

In the literature, the task of dysarthric speech intelligibility assessment has been approached through development of different low-level feature representations, subspace modeling, phone confidence estimation or measurement of automatic speech recognition system accuracy. This paper proposes a novel approach where the intelligibility is estimated as the percentage of correct words uttered by a speaker with dysarthria by matching and verifying utterances of the speaker with dysarthria against control speakers' utterances in phone posterior feature space and broad phonetic posterior feature space. Experimental validation of the proposed approach on the UA-Speech database, with posterior feature estimators trained on the data from auxiliary domain and language, obtained a best Pearson's correlation coefficient (r) of 0.950 and Spearman's correlation coefficient (ρ) of 0.957. Furthermore, replacing control speakers' speech with speech synthesized by a neural text-to-speech system obtained a best r of 0.937 and ρ of 0.961.

show abstract

Section: B Posterior Feature Estimatorsmentioning

confidence: 99%

“…In the Phonet toolkit 1 [28], these AFs are modeled by 18 off-the-shelf recurrent neural network (RNN) based binary classifiers, i.e. D = 18 × 2.…”

Section: A Phonetic Posterior Feature Representationsmentioning

confidence: 99%

See 1 more Smart Citation

Utterance Verification-Based Dysarthric Speech Intelligibility Assessment Using Phonetic Posterior Features

Fritsch

Magimai-Doss

2021

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

show abstract

“…A softmax activation function is used to compute the sequence of phoneme posterior probabilities = { 1 , 2 , … , T } . Bidirectional recurrent nets are used in this work because they have shown better results than standard GRUs in similar speech processing tasks [23,24].…”

Section: Recurrent Neural Network With Convolution Layersmentioning

confidence: 99%

Multi-channel spectrograms for speech processing applications using deep learning methods

Arias-Vergara

Klumpp

Vásquez-Correa

et al. 2020

Pattern Anal Applic

View full text Add to dashboard Cite

Time–frequency representations of the speech signals provide dynamic information about how the frequency component changes with time. In order to process this information, deep learning models with convolution layers can be used to obtain feature maps. In many speech processing applications, the time–frequency representations are obtained by applying the short-time Fourier transform and using single-channel input tensors to feed the models. However, this may limit the potential of convolutional networks to learn different representations of the audio signal. In this paper, we propose a methodology to combine three different time–frequency representations of the signals by computing continuous wavelet transform, Mel-spectrograms, and Gammatone spectrograms and combining then into 3D-channel spectrograms to analyze speech in two different applications: (1) automatic detection of speech deficits in cochlear implant users and (2) phoneme class recognition to extract phone-attribute features. For this, two different deep learning-based models are considered: convolutional neural networks and recurrent neural networks with convolution layers.

show abstract

“…The different phonemes of the Spanish language are grouped into 18 phonological posteriors. The phonological posteriors were computed with a bank of parallel recurrent neural networks to estimate the probability of occurrence of a specific phonological class [13].…”

Section: Speech Featuresmentioning

confidence: 99%

Comparison of User Models Based on GMM-UBM and I-Vectors for Speech, Handwriting, and Gait Assessment of Parkinson’s Disease Patients

Vásquez-Correa

Orozco-Arroyave

Nöth

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Parkinson's disease is a neurodegenerative disorder characterized by the presence of different motor impairments. Information from speech, handwriting, and gait signals have been considered to evaluate the neurological state of the patients. On the other hand, user models based on Gaussian mixture models -universal background models (GMM-UBM) and i-vectors are considered the state-of-the-art in biometric applications like speaker verification because they are able to model specific speaker traits. This study introduces the use of GMM-UBM and i-vectors to evaluate the neurological state of Parkinson's patients using information from speech, handwriting, and gait. The results show the importance of different feature sets from each type of signal in the assessment of the neurological state of the patients.

show abstract

Phonet: A Tool Based on Gated Recurrent Neural Networks to Extract Phonological Posteriors from Speech

Cited by 27 publications

References 15 publications

Utterance Verification-Based Dysarthric Speech Intelligibility Assessment Using Phonetic Posterior Features

Utterance Verification-Based Dysarthric Speech Intelligibility Assessment Using Phonetic Posterior Features

Multi-channel spectrograms for speech processing applications using deep learning methods

Comparison of User Models Based on GMM-UBM and I-Vectors for Speech, Handwriting, and Gait Assessment of Parkinson’s Disease Patients

Contact Info

Product

Resources

About