An Efficient Deep Learning Based Method for Speech Assessment of Mandarin-Speaking Aphasic Patients
The DOI matches its Crossref record; 47 of the 47 references it cites were found in a registry or an index.
Abstract
Speech assessment is an important part of the rehabilitation process for patients with aphasia (PWA). Mandarin speech lucidity features such as articulation, fluency, and tone influence the meaning of the spoken utterance and overall speech clarity. Automatic assessment of these features is important for an efficient assessment of the aphasic speech. Hence, in this paper, a standardized automatic speech lucidity assessment method for Mandarin-speaking aphasic patients using a machine learning based technique is presented. The proposed assessment method adopts the Chinese Rehabilitation Research Center Aphasia Examination (CRRCAE) standard as a guideline. Quadrature based high-resolution time-frequency images with a convolutional neural network (CNN) are utilized to develop a method that can map the relationship between the severity level of aphasic patients' speech and the three speech lucidity features. The results show a linear relationship with statistically significant correlations between the normalized true-class output activations (TCOA) of the CNN model and patients' articulation, fluency, and tone scores, i.e., 0.71 (p < 0.001), 0.60 (p < 0.001) and 0.58 (p < 0.001), respectively. The linearity of the proposed Mandarin aphasic speech assessment method and its significant correlation with the speech severity levels show the efficacy of the method in predicting the severity of impaired Mandarin speech. The outcome of this research envisages assisting speech-language pathologists in Mandarin-speech impairment assessment and promoting early support discharge; hence could alleviate the stress that the healthcare system is currently experiencing in China nationwide. The framework of the proposed Mandarin aphasic speech assessment method can be readily extended to other languages.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“With a large dataset for each aphasia type, classifiers can create distinct boundaries in the features space, resulting in high classification accuracy. Similarly, the CNN model will perform better with a large labeled dataset since it has better generalization in terms of feature extraction from high-resolution images [10].”
From Performance Evaluation of Machine Learning Frameworks for Aphasia Assessment (2021) · cites this paper as [10]
In the citing paper
“Generally, three types of training datasets are used for aphasia assessment tasks: (1) healthy subjects’ dataset, (2) aphasic patients’ dataset, or (3) a combination of healthy and aphasic dataset [10,12]”
From Performance Evaluation of Machine Learning Frameworks for Aphasia Assessment (2021) · cites this paper as [10]
In the citing paper
“The degradation in the performance of this model is due to the diversity of the aphasic dataset [10]. The recruited patients have different speech impairment severity levels, as reported in [10], that resulted in complex and unresolvable common features. Also, the aphasic multi-types (i.e., Global aphasia, Broca’s aphasia, Wernicke’s aphasia and Amnesic aphasia) speech datasets are scarce and”
From Performance Evaluation of Machine Learning Frameworks for Aphasia Assessment (2021) · cites this paper as [10]
In the citing paper
“Furthermore, the speech data were manually inspected, and all outliers (4% of the total dataset) were removed [10].”
From Performance Evaluation of Machine Learning Frameworks for Aphasia Assessment (2021) · cites this paper as [10]
In the citing paper
“The data collection environment for the healthy subjects and patients was largely consistent [10].”
From Performance Evaluation of Machine Learning Frameworks for Aphasia Assessment (2021) · cites this paper as [10]
21 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 3×
“Therefore, all TFD RGB color images were resized to 224 × 224 × 3 pixels and normalized as per ImageNet dataset characteristics, before feeding them to the pre-trained ResNet-34 CNN model [42].”
MethodInfluentialAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“999 with a cross-entropy loss function [44].”
Cyclical Learning Rates for Training Neural Networks
Smith, L. N. (2017) · 2017 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv.2017.58 · Cited by 2,670 · cited 2×
“03 [43].”
Method(1992) · Cited by 1,405
Understanding how image quality affects deep neural networks
Dodge, S., & Karam, L. (2016) · 2016 Eighth International Conference on Quality of Multimedia Experience (QoMEX) · doi:10.1109/qomex.2016.7498955 · Cited by 835 · cited 1×
“This will result in image distortion and resolution degradation and, consequently, a poor image classification performance [40], [41].”
BackgroundNovel Speech Signal Processing Algorithms for High-Accuracy Classification of Parkinson’s Disease
Tsanas, A., Little, M. A., McSharry, P. E., Spielman, J., & Ramig, L. O. (2012) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2012.2183367 · Cited by 732 · cited 3×
“For example, researchers in [24]–[26] used classical machine learning (CML) techniques such as support vector machines (SVM) and Gaussian Mixture Model (GMM) to assess speech disorder automatically.”
MethodIntensity of Aphasia Therapy, Impact on Recovery
Bhogal, S. K., Teasell, R., & Speechley, M. (2003) · Stroke · doi:10.1161/01.str.0000062343.64383.d0 · Cited by 719 · cited 1×
“Studiesindicated thatcommencinganintensiveguidedtreatmentattheacuteor sub-acutestageofaphasialeadstothehighestrecovery[17], [18] .”
Engelter, S. T., Gostynski, M., Papa, S., Frei, M., Born, C., Ajdacic-Gross, V., Gutzwiller, F., & Lyrer, P. A. (2006) · Stroke · doi:10.1161/01.str.0000221815.64093.8c · Cited by 688
Theory and Applications of Digital Speech Processing
Rabiner, L. R., & Schafer, R. W. (2010) · Medical Entomology and Zoology · Cited by 579
A meta-analysis of clinical outcomes in the treatment of aphasia
Robey, R. R. (1998) · Journal of Speech, Language, and Hearing Research · doi:10.1044/jslhr.4101.172 · Cited by 506 · cited 1×
“Studiesindicated thatcommencinganintensiveguidedtreatmentattheacuteor sub-acutestageofaphasialeadstothehighestrecovery[17], [18] .”
Bonita, R., Mendis, S., Truelsen, T., Bogousslavsky, J., Toole, J., & Yatsu, F. (2004) · The Lancet Neurology · doi:10.1016/s1474-4422(04)00800-2 · Cited by 437 · cited 1×
“I N RECENT years, cerebrovascular accident, also known as stroke, has become the second most common cause of death and the leading cause of ongoing disabilities worldwide [2], [3].”
BackgroundCommunication Partner Training in Aphasia: A Systematic Review
Simmons-Mackie, N., Raymer, A., Armstrong, E., Holland, A., & Cherney, L. R. (2010) · Archives of Physical Medicine and Rehabilitation · doi:10.1016/j.apmr.2010.08.026 · Cited by 325 · cited 1×
“Patients with aphasia (PWAs) often face significant communication difficulties, which may lead to feelings of frustration, loss of autonomy, and social isolation, among others [14].”
BackgroundBrain activation in the processing of Chinese characters and words: A functional MRI study
Tan, L. H., Spinks, J. A., Gao, J.-H., Liu, H.-L., Perfetti, C. A., Xiong, J., Stofer, K. A., Pu, Y., Liu, Y., & Fox, P. T. (2000) · Human Brain Mapping · doi:10.1002/(sici)1097-0193(200005)10:1<16::aid-hbm30>3.0.co;2-m · Cited by 303 · cited 2×
“Most aphasia patients are affected by the damage to the left hemisphere of the brain [58], [59], which is the dominant side for language functions for most people, resulting in impaired language function.”
BackgroundLam, J. M. C., & Wodchis, W. P. (2010) · Medical Care · doi:10.1097/mlr.0b013e3181ca2647 · Cited by 272 · cited 1×
“patients and Alzheimer patients [15], [16].”
Higher Cortical Functions in Man
Smith, A. (1967) · The Journal of Nervous and Mental Disease · doi:10.1097/00005053-196703000-00012 · Cited by 253
Development of convolutional neural network and its application in image classification: a survey
Wang, W., Yang, Y., Wang, X., Wang, W., & Li, J. (2019) · Optical Engineering · doi:10.1117/1.oe.58.4.040901 · Cited by 252 · cited 2×
“outstanding classification results in the field of computer vision [39].”
BackgroundNeural Plasticity: The Biological Substrate For Neurorehabilitation
Warraich, Z., & Kleim, J. A. (2010) · PM&R · doi:10.1016/j.pmrj.2010.10.016 · Cited by 226 · cited 1×
“A challenging and engaging rehabilitation program helps stroke patients recover faster from the disability due to stroke [47].”
BackgroundBasso, A. (2003) · doi:10.1093/oso/9780195135879.001.0001 · Cited by 170
Hussain, Z. M., & Boashash, B. (2002) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2002.800406 · Cited by 141 · cited 2×
“In [35], we found that the Hyperbolic T-distribution (HTD) [1] outperforms wavelet transform, Wigner-Ville distribution (WVD),Choi-Williamsdistribution(CWD)andtheExponential T-distribution(ETD),intermsofresolution,signal-to-noise (SNR)performanceandcross-termsreduction.”
BackgroundMethodManual of Aphasia and Aphasia Therapy
Helm‐Estabrooks, N., & Albert, M. L. (2013) · Medical Entomology and Zoology · Cited by 123
A comparative study of adaptive, automatic recognition of disordered speech
Christensen, H., Cunningham, S., Fox, C., Green, P., & Hain, T. (2012) · Interspeech 2012 · doi:10.21437/interspeech.2012-484 · Cited by 123 · cited 1×
“The challenges are abnormal speech patterns [54], speaker variability [55], and data scarcity [56].”
BackgroundA Functional Magnetic Resonance Imaging Study of Left Hemisphere Language Dominance in Children
Balsamo, L. M., Xu, B., Grandin, C. B., Petrella, J. R., Braniecki, S. H., Elliott, T. K., & Gaillard, W. D. (2002) · Archives of Neurology · doi:10.1001/archneur.59.7.1168 · Cited by 106 · cited 2×
“Most aphasia patients are affected by the damage to the left hemisphere of the brain [58], [59], which is the dominant side for language functions for most people, resulting in impaired language function.”
BackgroundPredictors of Emotional Distress After Stroke
Thomas, S. A., & Lincoln, N. B. (2008) · Stroke · doi:10.1161/strokeaha.107.498279 · Cited by 98 · cited 1×
“Aphasia is generally caused by a cerebrovascular accident and occurs in about one-third of the stroke patients [7], [8].”
BackgroundAutomatic quantitative analysis of spontaneous aphasic speech
Le, D., Licata, K., & Mower Provost, E. (2018) · Speech Communication · doi:10.1016/j.specom.2018.04.001 · Cited by 97 · cited 2×
“In several automatic speech assessment pieces of research, these standards were embraced as a guideline to assess aphasic patients [21]–[23], [31].”
BackgroundOnline crowdsourcing for efficient rating of speech: A validation study
McAllister Byun, T., Halpin, P. F., & Szeredi, D. (2015) · Journal of Communication Disorders · doi:10.1016/j.jcomdis.2014.11.003 · Cited by 95 · cited 1×
“Nevertheless, a previous study has shown that an untrained listener of a language can evaluate the lucidity of speech close to a specialist level [51].”
BackgroundEffects of Varying Resolution on Performance of CNN based Image Classification An Experimental Study
Kannojia, S. P., & Jaiswal, G. (2018) · International Journal of Computer Sciences and Engineering · doi:10.26438/ijcse/v6i9.451456 · Cited by 93 · cited 1×
“This will result in image distortion and resolution degradation and, consequently, a poor image classification performance [40], [41].”
BackgroundJia, Q., Liu, L., & Wang, Y. (2009) · Clinical and Experimental Pharmacology and Physiology · doi:10.1111/j.1440-1681.2009.05290.x · Cited by 75
Stroke In China, 1986 Through 1990
Cheng, X.-M., Ziegler, D. K., Lai, Y. C., Li, S.-C., Jiang, G.-X., Du, X., Wang, W., Wu, S., Bao, S.-G., & Bao, Q.-J. (1995) · Stroke · doi:10.1161/01.str.26.11.1990 · Cited by 75 · cited 1×
“According to the government report provided by the Ministry of Health of People’s Republic of China [4]–[6], there are 3 million new stroke incidents, and 1.5 million stroke-related deaths each year, and the total number of survivors has exceeded 8 million.”
BackgroundInfluentialSchaefer, S. M., Abercrombie, H. C., Lindgren, K. A., Larson, C. L., Ward, R. T., Oakes, T. R., Holden, J. E., Perlman, S. B., Turski, P. A., & Davidson, R. J. (2000) · Human Brain Mapping · doi:10.1002/(sici)1097-0193(200005)10:1<1::aid-hbm10>3.0.co;2-o · Cited by 70
Amami, R., & Smiti, A. (2017) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2016.08.021 · Cited by 63 · cited 4×
“For example, researchers in [24]–[26] used classical machine learning (CML) techniques such as support vector machines (SVM) and Gaussian Mixture Model (GMM) to assess speech disorder automatically.”
MethodInfluentialShinn, P., & Blumstein, S. E. (1983) · Brain and Language · doi:10.1016/0093-934x(83)90035-4 · Cited by 61 · cited 1×
“It is an acquired neurogenic language disorder in which an individual’s ability to produce or comprehend language is compromised [9], [10].”
BackgroundAutomatic Assessment of Speech Intelligibility for Individuals with Aphasia
Le, D., Licata, K., Persad, C., & Provost, E. M. (2016) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2016.2598428 · Cited by 59 · cited 4×
“Using feature extraction methods for the assessment of speech intelligibilityfeatures[48]makestheassessmentpronetopatient variability[55]effects.”
BackgroundMethodInfluentialComparing Humans and Automatic Speech Recognition Systems in Recognizing Dysarthric Speech
Mengistu, K. T., & Rudzicz, F. (2011) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-21043-3_36 · Cited by 55 · cited 1×
“The challenges are abnormal speech patterns [54],”
Stroke Rehabilitation in China: A Systematic Review and Meta-Analysis
Zhang, W. W., Speare, S., Churilov, L., Thuy, M., Donnan, G., & Bernhardt, J. (2014) · International Journal of Stroke · doi:10.1111/ijs.12029 · Cited by 50 · cited 1×
“According to the government report provided by the Ministry of Health of People’s Republic of China [4]–[6], there are 3 million new stroke incidents, and 1.5 million stroke-related deaths each year, and the total number of survivors has exceeded 8 million.”
BackgroundInfluentialTime-frequency analysis of normal and abnormal biological signals
Mahmoud, S. S., Hussain, Z. M., Cosic, I., & Fang, Q. (2006) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2006.02.001 · Cited by 50 · cited 2×
“In [35], we found that the Hyperbolic T-distribution (HTD) [1] outperforms wavelet transform, Wigner-Ville distribution (WVD),Choi-Williamsdistribution(CWD)andtheExponential T-distribution(ETD),intermsofresolution,signal-to-noise (SNR)performanceandcross-termsreduction.”
MethodSelf-citationWang, S., Wang, C., Zhang, N., Xiang, Y., Yang, Y., Shi, Y.-Z., Deng, Y., Zhu, M.-F., Liu, F., Yu, P., et al. (2018) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2018.00374 · Cited by 48 · cited 1×
“Researchers in [19] studied the association between post-stroke depression, aphasia, and”
BackgroundKlinik und Rehabilitation der Aphasie
Huber, W., Poeck, K., & Springer, L. (2013) · Thieme eBooks · doi:10.1055/b-002-57178 · Cited by 43 · cited 2×
“The conventional assessment and rehabilitation techniques of aphasia [30], [48]–[50] are resource-intensive and thus are un-sustainable due to the growing number of PWA.”
BackgroundMethodMustafa, M. B., Rosdi, F., Salim, S. S., & Mughal, M. U. (2015) · Expert Systems with Applications · doi:10.1016/j.eswa.2015.01.033 · Cited by 37 · cited 2×
“speaker variability [55], and data scarcity [56].”
MethodShahin, M., Ahmed, B., McKechnie, J., Ballard, K., & Gutierrez-Osuna, R. (2014) · Interspeech 2014 · doi:10.21437/interspeech.2014-377 · Cited by 34
Highly Accurate Mandarin Tone Classification In The Absence of Pitch Information
Ryant, N., Slaney, M., Liberman, M., Shriberg, E., & Yuan, J. (2014) · Speech Prosody 2014 · doi:10.21437/speechprosody.2014-123 · Cited by 32
Automatic Speech Assessment for People with Aphasia Using TDNN-BLSTM with Multi-Task Learning
Qin, Y., Lee, T., Feng, S., & Kong, A. P. H. (2018) · Interspeech 2018 · doi:10.21437/interspeech.2018-1630 · Cited by 30 · cited 1×
“In[22],theautomaticspeechassessment forPWAreliesonthemanualtranscriptionofaudiospeechinto Chinesecharacters.”
Qiu, W., Guan, H., Chen, Z., Yu, Y. T., Wu, H., Yu, W. S., Qiu, G.-R., Feng, X., & Lee, K. (2018) · Topics in Stroke Rehabilitation · doi:10.1080/10749357.2018.1544842 · Cited by 25 · cited 1×
“A research investigation found that aphasia patientshadthepoorestqualityoflife(QOL),followedbycancer patientsandAlzheimerpatients[15],[16].”
BackgroundLaw, S., Kong, A. P., & Lai, C. (2017) · Clinical Linguistics & Phonetics · doi:10.1080/02699206.2017.1334092 · Cited by 19 · cited 2×
“In [20], research using Cantonese AphasiaBank database was conducted to analyze samples from important event narrative task produced by speakers with fluent aphasia and their controls in terms of topic and vocabulary.”
BackgroundMethodA Chinese version of the Language Screening Test (CLAST) for early-stage stroke patients
Yang, H., Tian, S., Flamand‐Roze, C., Gao, L., Zhang, W., Li, Y., Wang, J., Sun, Z., Su, Y., Zhao, L., et al. (2018) · PLoS ONE · doi:10.1371/journal.pone.0196646 · Cited by 17 · cited 1×
“Overall, the major issues being faced in aphasia assessment and rehabilitation, especially in China, are 1) least attention is given to research on accurate speech impairment severity level assessment methods, 2) lack of reliable and standardized automatic tools to be used during assessment and rehabilitation for Mand…”
BackgroundSelf-citationWord accent and intonation in Baltic
Hualde, J. I., & Riad, T. (2014) · Speech prosody · doi:10.21437/speechprosody.2014-122 · Cited by 12 · cited 1×
“A total of 51 features based onMel Frequency Cepstral Coefficients (MFCCs), the formant frequencies, and signal energy were calculated for the classification [36]–[38].”
MethodMandarin Vowels Revisited: Evidence from Electromagnetic Articulography
Wu, C.-H., & Shih, C. (2009) · Proceedings of the Annual Meeting of the Berkeley Linguistics Society · doi:10.3765/bls.v35i1.3622 · Cited by 9
Towards Automatic Speech-Language Assessment for Aphasia Rehabilitation
Le, D. (2017) · Deep Blue (University of Michigan) · Cited by 3
Research works printed but not linked: 9
- li, 2000, Hanyu biaozhun shiyuzheng jianchafa de bianzhi yu changmo [The establishment and normalization of the Chinese standard for aphasia examination], Zhongguo Kangfu Lilun Yu Shijian, 6, 162
- mahmoud, 2019, Automatic mandarin vowels recognition framework for aphasic patients rehabilitation, Proc 13th IEEE-EMBS Int Summer School Symp Med Dev Biosensors (MDBS2019)
- zhang, 2005, Zhongguo kangfu yanjiu Zhongxin hanyu biaozhun shiyuzheng jiancha liangbiao de xindu yu xiaodu fenxi [The Reliability and validity analysis for the Chinese standard for aphasia scale by China Rehabilitation Research Center], Zhongguo Kangfu Lilun Yu Shijian, 11, 703
- huang, 2007, Youce danao banqiu yuyan gongneng [The language function of right hemisphere], Zhongguo Shenjing Mianyixue He Shenjingbingxue Zazhi, 14, 310
- ding, 1995, Jisuanji fuzhu yanyu jiaozhi xitong [A computer aided speech correction system], Zhongguo Shengwu Yixue Gongcheng Xuebao, 14, 39
- 10.1002/(SICI)1097-0193(200005)10:1<16::AID-HBM30>3.3.CO;2-D · doi:10.1002/(sici)1097-0193(200005)10:1<16::aid-hbm30>3.3.co;2-d
- jiaoyanshi, 1993, Xian dai han yu [Modern Chinese]
- cheng, 2005, Xian dai han yu [Modern Chinese]
- davis, 2007, Aphasiology Disorders and clinical practice
Cited by
AI Applications in Adult Stroke Recovery and Rehabilitation: A Scoping Review Using AI
Senadheera, I., Hettiarachchi, P., Haslam, B. S., Nawaratne, R., Sheehan, J., Lockwood, K. J., Alahakoon, D., & Carey, L. M. (2024) · Sensors · doi:10.3390/s24206585 · Cited by 111
“Furthermore, ANNs have been used to evaluate tone production in Mandarin-speaking patients with post-stroke dysarthria, demonstrating comparable recognition rates compared to human listeners [82].”
BackgroundMahmoud, S. S. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3284133 · Cited by 37
“In this article, all TFD grayscale images of intrusions and nuisances were resized to 224 × 224 × 1 pixels and normalized according to the characteristics of the ImageNet dataset [39], [40].”
MethodInfluentialSelf-citationPerformance Evaluation of Machine Learning Frameworks for Aphasia Assessment
Mahmoud, S. S., Kumar, A., Li, Y., Tang, Y., & Fang, Q. (2021) · Sensors · doi:10.3390/s21082582 · Cited by 27
“In [10], we collected Mandarin datasets from healthy subjects and aphasic patients.”
BackgroundMethodInfluentialSelf-citationMahmoud, S. S., Pallaud, R. F., Kumar, A., Faisal, S., Wang, Y., & Fang, Q. (2023) · Sensors · doi:10.3390/s23020857 · Cited by 25
“, 2020 [11] DNN: Convolutional Neural Network (CNN) • The aim was to assess the severity of impairment in Mandarin-speaking aphasic patients.”
InfluentialSelf-citationAI-assisted assessment and treatment of aphasia: a review
Zhong, X. (2024) · Frontiers in Public Health · doi:10.3389/fpubh.2024.1401240 · Cited by 25
Metadata
- Authors
- Mahmoud, S. S., Kumar, A., Tang, Y., Li, Y., Gu, X., Fu, J., & Fang, Q.
- Affiliations
- Shantou University (CN)
- RMIT University (AU)
- Venue
- IEEE Journal of Biomedical and Health Informatics
- Published
- 2020-11
- Volume
- 24
- Issue
- 11
- Pages
- 3191-3202
- ISSN
- 2168-2194 (ISSN-L)
- 2168-2208
- OpenAlex
- W3045355365
- Semantic Scholar
- bcd5c6802fae9aa65943983c62be20a7cdd78a24
- Cited by
- 36
- References
- 47
- Citations by year
- 2026: 3 · 2025: 4 · 2024: 10 · 2023: 7 · 2022: 8 · 2021: 2 · 2020: 2
- FWCI
- 2.85
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Journal of Biomedical and Health Informatics (publishedVersion)
- PubMed (publishedVersion)
- RMIT Research Repository (RMIT University Library) (submittedVersion)
- Figshare (submittedVersion)
- Funders
- Li Ka Shing Foundation Cross-Disciplinary Research (2020LKSFG04C)
- Topics
- Health Sciences › Health Professions › Speech and Hearing › Voice and Speech Disorders
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Life Sciences › Neuroscience › Cognitive Neuroscience › Neurobiology of Language and Bilingualism
- Keywords
- aphasia, Mandarin speech, speech assessment, articulation, fluency, tone, convolutional neural networks, time-frequency images, speech-language pathology
- MeSH terms
- Deep Learning, Aphasia, Humans, Language, Speech, Neural Networks, Computer
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.