An Utterance Verification System for Word Naming Therapy in Aphasia

Abstract

Anomia (word finding difficulties) is the hallmark of aphasia an acquired language disorder, most commonly caused by stroke. Assessment of speech performance using pijcture naming tasks is therefore a key method for identification of the disorder and monitoring patient's response to treatment interventions. Currently, this assessment is conducted manually by speech and language therapists (SLT). Surprisingly, despite advancements in ASR and artificial intelligence with technologies like deep learning, research on developing automated systems for this task has been scarce. Here we present an utterance verification system incorporating a deep learning element that classifies 'correct'/'incorrect' naming attempts from aphasic stroke patients. When tested on 8 native British-English speaking aphasics the system's performance accuracy ranged between 83.6% to 93.6%, with a 10 fold cross validation mean of 89.5%. This performance was not only significantly better than one of the leading commercially available ASRs (Google speech-to-text service) but also comparable in some instances with two independent SLT ratings for the same dataset.

A Systematic Review of Using Deep Learning in Aphasia: Challenges and Future Directions

“…Speech patterns can vary significantly among individuals with aphasia, even those with similar clinical diagnoses [20]. Factors such as the type and severity of aphasia, cognitive abilities, and other individual differences contribute to this variability [21].…”

“…Factors such as the type and severity of aphasia, cognitive abilities, and other individual differences contribute to this variability [21]. As a result, automatic speech recognition systems must be robust enough to adapt to these individual differences and accurately assess speech performance across a diverse population of individuals with aphasia [20,21].…”

“…Aphasic speech often contains linguistic abnormalities such as paraphasic errors (substitution, addition, or omission of sounds or words), neologisms (novel or nonsensical words), and agrammatism (difficulty with grammar and sentence structure) [18,19]. These abnormalities pose challenges for automatic speech recognition systems, as they must be able to accurately recognize and interpret these linguistic features to assess speech performance effectively [20]. Incorporating algorithms capable of handling such linguistic complexity is essential for improving recognition accuracy [18,[20][21][22].…”

Intelligent speech technologies for transcription, disease diagnosis, and medical equipment interactive control in smart hospitals: A review

“…As shown in Table 4 , many studies use speech technology to diagnose diseases that cause voice problems [ 157 ]. The diseases include Voice disorder [ 99 ], Acute decompensated heart failure [ 100 ], Alzheimer's Disease (AD) [ 104 ], Dysphonia [ 118 ], Parkinson's Disease (PD) [ 122 , [125] , [126] , [127] , [128] ], Stroke [ 125 , 224 ], COVID-19 [ 130 , 132 , 135 ], Chronic Obstructive Pulmonary Disease [ 142 , 143 ], Aphasia [ 169 , 170 , 181 ], Tuberculosis (TB) [ [147] , [148] , [149] ], and organ lesions such as oral cancer [ 158 ], head and neck cancer [ 159 ], nodules, polyps, and Reinke's edema [ 95 ]. These studies are divided into four categories by diseases, including the otorhinolaryngology department, respiratory department, neurology department, and others, and are shown in the four sub-tables, respectively.…”

“…As shown in Fig. 17 , Barbera et al obtained the posterior probability of the patient's speech according to the acoustic model trained by a DNN network, compared it with the posterior probability of normal speech, and used the DTW algorithm to calculate the distance for classification [ 169 , 170 ]. The combination of DNN and vector matching method achieved a good result on the speech of word naming tests, which inspires us to integrate traditional methods with recent ones.…”