Automatic dysfluency detection in dysarthric speech using deep belief networks

Oue, Stacey; Marxer, Ricard; Rudzicz, Frank

doi:10.18653/v1/w15-5111

Cited by 28 publications

(9 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…45 MFCC and 14 LPCC features from TORGO dataset [72] has been used in this case study for the detection of disfluencies [72]. The experimental results obtained showed that MFCCs and LPCCs produce similar detection accuracies of approximately 86% for repetitions and 84% for non-speech disfluencies [105].…”

Section: Statistical Approachesmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning for Stuttering Identification: Review, Challenges and Future Directions

Sheikh¹,

Sahidullah²,

Hirsch³

et al. 2021

Preprint

View full text Add to dashboard Cite

Stuttering is a speech disorder during which the flow of speech is interrupted by involuntary pauses and repetition of sounds. Stuttering identification is an interesting interdisciplinary domain research problem which involves pathology, psychology, acoustics, and signal processing that makes it hard and complicated to detect. Recent developments in machine and deep learning have dramatically revolutionized speech domain, however minimal attention has been given to stuttering identification. This work fills the gap by trying to bring researchers together from interdisciplinary fields. In this paper, we review comprehensively acoustic features, statistical and deep learning based stuttering/disfluency classification methods. We also present several challenges and possible future directions.

show abstract

Section: Statistical Approachesmentioning

confidence: 99%

“…In 2005, Oue et al [105] introduced deep belief network for the automatic detection of repetitions, non-speech disfluencies. 45 MFCC and 14 LPCC features from TORGO dataset [72] has been used in this case study for the detection of disfluencies [72].…”

Section: Statistical Approachesmentioning

confidence: 99%

Machine Learning for Stuttering Identification: Review, Challenges and Future Directions

Sheikh¹,

Sahidullah²,

Hirsch³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Due to recent advancements in deep learning, the improvement in speech technology surpasses the shallow neural network based approaches, and thus, resulted in a shift towards deep learning based framework and, disfluency identification is no exception. The work in [19] used deep belief networks with cepstral features for the detection of repetitions and stop gaps on TORGO dataset. T. Kourkounakis et al [20] introduced a deep residual neural network and bi-directional long term short memory (ResNet+BiLSTM) based method to learn stutterspecific features from the audio.…”

Section: Related Workmentioning

confidence: 99%

StutterNet: Stuttering Detection Using Time Delay Neural Network

Sheikh¹,

Sahidullah²,

Hirsch³

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper introduce StutterNet, a novel deep learning based stuttering detection capable of detecting and identifying various types of disfluencies. Most of the existing work in this domain uses automatic speech recognition (ASR) combined with language models for stuttering detection. Compared to the existing work, which depends on the ASR module, our method relies solely on the acoustic signal. We use a time-delay neural network (TDNN) suitable for capturing contextual aspects of the disfluent utterances. We evaluate our system on the UCLASS stuttering dataset consisting of more than 100 speakers. Our method achieves promising results and outperforms the state-ofthe-art residual neural network based method. The number of trainable parameters of the proposed method is also substantially less due to the parameter sharing scheme of TDNN.

show abstract

“…Gauthier, Shippagan, NB, E8S 1P6, Canada Full list of author information is available at the end of the article signal and Gaussian Mixture Models (GMMs) to model the distribution of the spectral representation of a waveform. However, HMM-GMM-based systems require a large amount of data to be trained, which is not efficient in the case of dysarthric speech where the corpora used for training are always small [6]. Therefore, these approaches cannot be applied with ease in the context of dysarthric speech.…”

Section: Related Workmentioning

confidence: 99%

Improving dysarthric speech recognition using empirical mode decomposition and convolutional neural network

Yakoub

Selouani

Zaidi

et al. 2020

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

In this paper, we use empirical mode decomposition and Hurst-based mode selection (EMDH) along with deep learning architecture using a convolutional neural network (CNN) to improve the recognition of dysarthric speech. The EMDH speech enhancement technique is used as a preprocessing step to improve the quality of dysarthric speech. Then, the Mel-frequency cepstral coefficients are extracted from the speech processed by EMDH to be used as input features to a CNN-based recognizer. The effectiveness of the proposed EMDH-CNN approach is demonstrated by the results obtained on the Nemours corpus of dysarthric speech. Compared to baseline systems that use Hidden Markov with Gaussian Mixture Models (HMM-GMMs) and a CNN without an enhancement module, the EMDH-CNN system increases the overall accuracy by 20.72% and 9.95%, respectively, using a k-fold cross-validation experimental setup.

show abstract

Automatic dysfluency detection in dysarthric speech using deep belief networks

Cited by 28 publications

References 10 publications

Machine Learning for Stuttering Identification: Review, Challenges and Future Directions

Machine Learning for Stuttering Identification: Review, Challenges and Future Directions

StutterNet: Stuttering Detection Using Time Delay Neural Network

Improving dysarthric speech recognition using empirical mode decomposition and convolutional neural network

Contact Info

Product

Resources

About