Automatic Recognition System for Dysarthric Speech Based on MFCC’s, PNCC’s, JITTER and SHIMMER Coefficients

Zaidi, Brahim-Fares; Boudraa, Malika; Selouani, Sid‐Ahmed; Addou, Djamel; Yakoub, Mohammed Sidi

doi:10.1007/978-3-030-17798-0_40

Cited by 3 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [25], the authors showed that voice quality features are relevant markers signaling paralinguistic information, and that they should even be considered as prosodic parameters along with pitch and duration, for instance. It has been demonstrated that prosodic information can increase the performance of automatic speech recognition systems, like in [26], where the authors built an ASR for dysarthric speech, or [27], where the authors applied jitter and shimmer for noisy speech recognition, both of them using HMM models. Also, a neural network approach with LSTMs was taken by [28], for acoustic emotion recognition task, however they did not perform ASR task on its own.…”

Section: Voice Featuresmentioning

confidence: 99%

Convolutional Speech Recognition with Pitch and Voice Quality Features

Cámbara,

Luque,

Farrús

2020

Preprint

View full text Add to dashboard Cite

The effects of adding pitch and voice quality features such as jitter and shimmer to a state-of-the-art CNN model for Automatic Speech Recognition are studied in this work. Pitch features have been previously used for improving classical HMM and DNN baselines, while jitter and shimmer parameters have proven to be useful for tasks like speaker or emotion recognition. Up to our knowledge, this is the first work combining such pitch and voice quality features with modern convolutional architectures, showing improvements up to 2% absolute WER points, for the publicly available Spanish Common Voice dataset. Particularly, our work combines these features with mel-frequency spectral coefficients (MFSCs) to train a convolutional architecture with Gated Linear Units (Conv GLUs). Such models have shown to yield small word error rates, while being very suitable for parallel processing for online streaming recognition use cases. We have added pitch and voice quality functionality to Facebook's wav2letter speech recognition framework, and we provide with such code and recipes to the community, to carry on with further experiments. Besides, to the best of our knowledge, our Spanish Common Voice recipe is the first public Spanish recipe for wav2letter.

show abstract

Section: Voice Featuresmentioning

confidence: 99%