The Nemours database of dysarthric speech

Menéndez-Pidal, Xavier; Polikoff, James B.; Peters, Stanley; Leonzio, J.E.; Bunnell, H. Timothy

doi:10.1109/icslp.1996.608020

Cited by 129 publications

(96 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regarding disordered speech, some previous corpora have been acquired for studies in dysarthic speech like Nemours (Menéndez-Pidal et al, 1996), a research corpus of 814 short sentences in English from 11 dysarthric speakers, and the corpus for the STARDUST project (Hawley et al, 2003) (Kim et al, 2008) is a massive corpus containing several hours of speech from 10 individuals with different degrees of dysarthria. In languages different from English, it can be referred also efforts of speech acquistion in Dutch (Sanders et al, 2002), and regarding Spanish, the most remarkable effort was done in the HACRO project (Navarro-Mesa et al, 2005), containing speech from speakers of different ages with different speech impairments for the development of a tool for the evaluation of oral utterances.…”

Section: A Novel Corpus Of Impaired Speech From Children and Young Admentioning

confidence: 99%

Tools and Technologies for Computer-Aided Speech and Language Therapy

Saz

Yin

Lleida

et al. 2009

Speech Communication

View full text Add to dashboard Cite

Section: A Novel Corpus Of Impaired Speech From Children and Young Admentioning

confidence: 99%

Tools and Technologies for Computer-Aided Speech and Language Therapy

Saz

Yin

Lleida

et al. 2009

Speech Communication

View full text Add to dashboard Cite

“…Past ASR experiments on dysarthric speech mostly included GMM-HMM systems [15][16][17][18][19][20]. More recently Lee et al [21] reported ASR performance on Cantonese aphasic speech and disordered voice.…”

Section: Introductionmentioning

confidence: 99%

Multi-Stage DNN Training for Automatic Recognition of Dysarthric Speech

Yılmaz¹,

Ganzeboom²,

Cucchiarini³

et al. 2017

Interspeech 2017

View full text Add to dashboard Cite

Incorporating automatic speech recognition (ASR) in individualized speech training applications is becoming more viable thanks to the improved generalization capabilities of neural network-based acoustic models. The main problem in developing applications for dysarthric speech is the relative in-domain data scarcity. Collecting representative amounts of dysarthric speech data is difficult due to rigorous ethical and medical permission requirements, problems in accessing patients who are generally vulnerable and often subject to altering health conditions and, last but not least, the high variability in speech resulting from different pathological conditions. Developing such applications is even more challenging for languages which in general have fewer resources, fewer speakers and, consequently, also fewer patients than English, as in the case of a mid-sized language like Dutch. In this paper, we investigate a multi-stage deep neural network (DNN) training scheme aimed at obtaining better modeling of dysarthric speech by using only a small amount of in-domain training data. The results show that the system employing the proposed training scheme considerably improves the recognition of Dutch dysarthric speech compared to a baseline system with single-stage training only on a large amount of normal speech or a small amount of in-domain data.

show abstract

“…The single word stimuli in the database include repetitions of English digits, the international radio alphabets, the 20 most frequent words in the British National Corpus (BNC), and a set of words selected to demonstrate relevant phonetic contrasts [21]. Other databases such as UA-Speech database [22] or Nemours database [23] mainly contain isolated words, acoustic samples of digits, radio alphabet letters, and computer commands, which is inadequate to build a continuous dysarthric speech recognition model.…”

Section: Materials and Feature Descriptionmentioning

confidence: 99%

An Automatic Dysarthric Speech Recognition Approach using Deep Neural Networks

Ren¹,

Liu²

2017

ijacsa

View full text Add to dashboard Cite

Abstract-Transcribing dysarthric speech into text is still a challenging problem for the state-of-the-art techniques or commercially available speech recognition systems. Improving the accuracy of dysarthric speech recognition, this paper adopts Deep Belief Neural Networks (DBNs) to model the distribution of dysarthric speech signal. A continuous dysarthric speech recognition system is produced, in which the DBNs are used to predict the posterior probabilities of the states in Hidden Markov Models (HMM) and the Weighted Finite State Transducers framework was utilized to build the speech decoder. Experimental results show that the proposed method provides better prediction of the probability distribution of the spectral representation of dysarthric speech that outperforms the existing methods, e.g., GMM-HMM based dysarthric speech recogniztion approaches. To the best of our knowledge, this work is the first time to build a continuous speech recognition system for dysarthric speech with deep neural network technique, which is a promising approach for improving the communication between those individuals with speech impediments and normal speakers.

show abstract

The Nemours database of dysarthric speech

Cited by 129 publications

References 5 publications

Tools and Technologies for Computer-Aided Speech and Language Therapy

Tools and Technologies for Computer-Aided Speech and Language Therapy

Multi-Stage DNN Training for Automatic Recognition of Dysarthric Speech

An Automatic Dysarthric Speech Recognition Approach using Deep Neural Networks

Contact Info

Product

Resources

About