Speech recognition in Alzheimer's disease with personal assistive robots

Rudzicz, Frank; Wang, Rosalie H.; Begum, Momotaz; Mihailidis, Alex

doi:10.3115/v1/w14-1904

Cited by 16 publications

(20 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One issue that arises with ASR is the introduction of word recognition errors: insertions, deletions, and substitutions. This problem as it relates to impaired speech has been considered elsewhere (Jarrold et al, 2014;Fraser et al, 2013;Rudzicz et al, 2014), although more work is needed. Another issue, which we address here, is how ASR transcripts are divided into sentences.…”

Section: Introductionmentioning

confidence: 99%

Sentence segmentation of aphasic speech

Fraser¹,

Ben-David²,

Hirst³

et al. 2015

Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

Automatic analysis of impaired speech for screening or diagnosis is a growing research field; however there are still many barriers to a fully automated approach. When automatic speech recognition is used to obtain the speech transcripts, sentence boundaries must be inserted before most measures of syntactic complexity can be computed. In this paper, we consider how language impairments can affect segmentation methods, and compare the results of computing syntactic complexity metrics on automatically and manually segmented transcripts. We find that the important boundary indicators and the resulting segmentation accuracy can vary depending on the type of impairment observed, but that results on patient data are generally similar to control data. We also find that a number of syntactic complexity metrics are robust to the types of segmentation errors that are typically made.

show abstract

Section: Introductionmentioning

confidence: 99%

Sentence segmentation of aphasic speech

Fraser¹,

Ben-David²,

Hirst³

et al. 2015

Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

show abstract

“…-The robot's ability to speak and understand speech; if it could talk, is the robot multilingual? [92] claims robots need to communicate with the elderly to provide care and companionship; -Different aspects of the robot's vision-based capabilities for functionalities. We assess whether the robot can detect faces, recognise them, and understand the environment to gaze at the elderly and understand their facial emotions; -Nadine's conversational and empathetic capabilities visà-vis other robots.…”

Section: Conclusion Of the Sar Choice Of Humanoid Robot And Research Questionsmentioning

confidence: 99%

“…-If previous robots were capable of engaging the elderly using memory. The ability to give reminders and remember past conversations to initiate and sustain personalised conversations is crucial to a robot's ability to provide companionship to the elderly [92]). Having a longterm memory would allow Nadine to create a high-level behavioural system, enabling her to interact with the elderly in richer forms.…”

Section: Conclusion Of the Sar Choice Of Humanoid Robot And Research Questionsmentioning

confidence: 99%

Can a humanoid social robot stimulate the interactivity of cognitively impaired elderly? A thorough study based on computer vision methods

et al. 2021

View full text Add to dashboard Cite

Social Assistive Robotics is increasingly being used in care settings to provide psychosocial support and interventions for the elderly with cognitive impairments. Most of these social robots have provided timely stimuli to the elderly at home and in care centres, including keeping them active and boosting their mood. However, previous investigations have registered shortcomings in these robots, particularly in their ability to satisfy an essential human need: the need for companionship. Reports show that the elderly tend to lose interests in these social robots after the initial excitement as the novelty wears out and the monotonous familiarity becomes all too familiar. This paper presents our research facilitating conversations between a social humanoid robot, Nadine, and cognitively impaired elderly at a nursing home. We analysed the effectiveness of human–humanoid interactions between our robot and 14 elderly over 29 sessions. We used both objective tools (based on computer vision methods) and subjective tools (based on observational scales) to evaluate the recorded videos. Our findings showed that our subjects engaged positively with Nadine, suggesting that their interaction with the robot could improve their well-being by compensating for some of their emotional, cognitive, and psychosocial deficiencies. We detected emotions associated with cognitively impaired elderly during these interactions. This study could help understand the expectations of the elderly and the current limitations of Social Assistive Robots. Our research is aligned with all the ethical recommendations by the NTU Institutional Review Board.

show abstract

“…For these reasons, there has been limited research conducted on speech recognition system development for NCD screening. In order to address the data scarcity issue, in-house collected data was previously exploited in system development [4,17]. However, compared with the rapid progress of speech recognition performance on non-aged adult speech, there is a notable lack of systems purposefully developed for elderly speech data targeting NCD diagnosis [4,17,18,19,20].…”

Section: Introductionmentioning

confidence: 99%

Development of the Cuhk Elderly Speech Recognition System for Neurocognitive Disorder Detection Using the Dementiabank Corpus

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Early diagnosis of Neurocognitive Disorder (NCD) is crucial in facilitating preventive care and timely treatment to delay further progression. This paper presents the development of a state-of-the-art automatic speech recognition (ASR) system built on the Dementia-Bank Pitt corpus for automatic NCD detection. Speed perturbation based audio data augmentation expanded the limited elderly speech data by four times. Large quantities of out-of-domain, non-aged adult speech were exploited by cross-domain adapting a 1000-hour LibriSpeech corpus trained LF-MMI factored TDNN system to De-mentiaBank. The variability among elderly speakers was modeled using i-Vector and learning hidden unit contributions (LHUC) based speaker adaptive training. Robust Bayesian estimation of TDNN systems and LHUC transforms were used in both cross-domain and speaker adaptation. A Transformer language model was also built to improve the final system performance. A word error rate (WER) reduction of 11.72% absolute (26.11% relative) was obtained over the baseline i-Vector adapted LF-MMI TDNN system on the evaluation data of 48 elderly speakers. The best NCD detection accuracy of 88%, comparable to that using the ground truth speech transcripts, was obtained using the textual features extracted from the final ASR system outputs.

show abstract

Speech recognition in Alzheimer's disease with personal assistive robots

Cited by 16 publications

References 29 publications

Sentence segmentation of aphasic speech

Sentence segmentation of aphasic speech

Can a humanoid social robot stimulate the interactivity of cognitively impaired elderly? A thorough study based on computer vision methods

Development of the Cuhk Elderly Speech Recognition System for Neurocognitive Disorder Detection Using the Dementiabank Corpus

Contact Info

Product

Resources

About