Phonetic Analysis of Dysarthric Speech Tempo and Applications to Robust Personalised Dysarthric Speech Recognition

Xiong, Feifei; Barker, Jon; Christensen, Heidi

doi:10.1109/icassp.2019.8683091

Cited by 56 publications

(63 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 1 shows how speaking rate and WER are correlated. We approximate speaking rate information by computing mean phoneme durations from forced alignments of the training data with the methodology of Xiong et al [22]. It can be seen that dysarthric speakers have the lowest speaking rates and also the highest WERs.…”

Section: -Wordmentioning

confidence: 99%

“…typical speech [2,10,13,23]. Other works investigated transforming pathological speech to be more similar to typical speech, for example with speech enhancement methods [1] or by adjusting speech tempo [22]. Alternatively, Jiao et al [6], Xiong et al [22] have also employed data augmentation techniques to create additional, artifical dysarthric speech data.…”

Section: Introductionmentioning

confidence: 99%

“…Other works investigated transforming pathological speech to be more similar to typical speech, for example with speech enhancement methods [1] or by adjusting speech tempo [22]. Alternatively, Jiao et al [6], Xiong et al [22] have also employed data augmentation techniques to create additional, artifical dysarthric speech data. As many speech disorders affect the movement of articulators in the vocal tract, modelling articulatory information has been found to be beneficial [5,19,24].…”

Section: Introductionmentioning

confidence: 99%

“…The use of such sequencediscriminative criteria has not been sufficiently explored in the context of pathological speech yet. LF-MMI has previously been applied to dysarthric speech [22], but its performance in comparison with other methods has not yet been analysed in detail.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Dysarthric Speech Recognition with Lattice-Free MMI

Hermann

Magimai.-Doss

2020

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

View full text Add to dashboard Cite

Recognising dysarthric speech is a challenging problem as it differs in many aspects from typical speech, such as speaking rate and pronunciation. In the literature the focus so far has largely been on handling these variabilities in the framework of HMM/GMM and cross-entropy based HMM/DNN systems. This paper focuses on the use of state-of-the-art sequencediscriminative training, in particular lattice-free maximum mutual information (LF-MMI), for improving dysarthric speech recognition. Through a systematic investigation on the Torgo corpus we demonstrate that LF-MMI performs well on such atypical data and compensates much better for the low speaking rates of dysarthric speakers than conventionally trained systems. This can be attributed to inherent aspects of current speech recognition training regimes, like frame subsampling and speed perturbation, which obviate the need for some techniques previously adopted specifically for dysarthric speech.

show abstract

Section: -Wordmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Dysarthric Speech Recognition with Lattice-Free MMI

Hermann

Magimai.-Doss

2020

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

View full text Add to dashboard Cite

show abstract

“…According to these assumptions, we propose a method to transfer the knowledge learned from these rich speech data sources to the problem of Japanese dysarthric speech recognition, for which training data is insufficient. Utilization of the speech data from physically unimpaired persons who speak the same language as the target speaker has been considered in some literatures [13]- [15]. However, these studies only considered the linguistic characteristics within the language.…”

Section: Depictsmentioning

confidence: 99%

Knowledge Transferability Between the Speech Data of Persons With Dysarthria Speaking Different Languages for Dysarthric Speech Recognition

Takashima

Takiguchi

et al. 2019

IEEE Access

View full text Add to dashboard Cite

In this paper, we present an end-to-end speech recognition system for Japanese persons with articulation disorders resulting from athetoid cerebral palsy. Because their utterance is often unstable or unclear, speech recognition systems struggle to recognize their speech. Recent deep learningbased approaches have exhibited promising performance. However, these approaches require a large amount of training data, and it is difficult to collect sufficient data from such dysarthric people. This paper proposes a transfer learning method that transfers two types of knowledge corresponding to the different datasets: the language-dependent (phonetic and linguistic) characteristic of unimpaired speech and the language-independent characteristic of dysarthric speech. The former is obtained from Japanese non-dysarthric speech data, and the latter is obtained from non-Japanese dysarthric speech data. In the proposed method, we pre-train a model using Japanese non-dysarthric speech and non-Japanese dysarthric speech, and thereafter, we fine-tune the model using the target Japanese dysarthric speech. To handle the speech data of the two different languages in one model, we employ language-specific decoder modules. Experimental results indicate that our proposed approach can significantly improve speech recognition performance compared with other approaches that do not use additional speech data. INDEX TERMS Assistive technology, deep learning, dysarthria, end-to-end model, knowledge transfer, multilingual, speech processing, speech recognition.

show abstract