Real-time vibration control of an electrolarynx based on statistical F&lt;inf&gt;0&lt;/inf&gt; contour prediction

Tanaka, Kou; Toda, Tomoki; Neubig, Graham; Nakamura, Satoshi

doi:10.1109/eusipco.2016.7760465

Cited by 2 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the literature of EL speech enhancement, statistical F0 prediction based on Gaussian mixture models (GMMs) [3,4,5], and F0 prediction using neural networks [6] have been proposed for enhancing naturalness of the EL speech. In statistical F0 prediction, a parallel dataset consisting of utterance pairs of EL speech and normal speech is developed in advance and a twostep training-prediction process is performed to predict F0 contours from segmental spectral features.…”

Section: Related Workmentioning

confidence: 99%

“…They have furthermore introduced an EL-air speech system in which F0 contours can be controlled by using an air-pressure sensor. In [5], the authors have developed a real-time statistical F0 contour prediction system for vibration control of the electrolarynx. This system, in turn, uses segmental spectral features to predict F0 contours, and moreover, predicts forthcoming F0 values to control F0 patterns of the excitation signals.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Investigation of Features for Fundamental Frequency Pattern Prediction in Electrolaryngeal Speech Enhancement

Eshghi¹,

Tanaka²,

Kobayashi³

et al. 2019

10th ISCA Workshop on Speech Synthesis (SSW 10)

Self Cite

View full text Add to dashboard Cite

Despite abundance of research, natural voice restoration after total laryngectomy (i. e., removal of the vocal folds of the larynx), has remained a challenge. A typical way of producing a relatively intelligible speech for patients suffering from this inability is to use an electrolarynx. However, the outcome voice sounds artificial and has "robotic" quality owing to constant fundamental frequency (F0) patterns generated by the electrolarynx. In existing frameworks on natural F0 patterns prediction, a model is trained on a massive amount of parallel training data to find a mapping that maps spectral features of the source speech into F0 contours of the target speech. However, creating big datasets for electrolaryngeal (EL) speech is considered as a cumbersome and expensive task. Moreover, EL speech spectral features are significantly different from spectral features of the normal speech, and therefore, it is not straightforward to effectively use easily available normal speech datasets in training of the model for EL speech. Consequently, the quality of the models could be still low due to the lack of sufficient training data. To address this problem, we investigate F0 pattern prediction based on other features that could be shared between normal speech and EL speech. By using shared input features, we would be to train the prediction model using a large amount of training data. As such features, in this work, we examine F0 prediction accuracy based on phoneme-related features. The findings show that by considering phoneme labels for both vowels and consonants and one-hot encoding of these labels, we are able to predict F0 contours with high correlation coefficients.

show abstract