The Montreal cognitive assessment (MoCA), a widely accepted screening tool for identifying patients with mild cognitive impairment (MCI), includes a language fluency test of verbal functioning; its scores are based on the number of unique correct words produced by the test taker. However, it is possible that unique words may be counted differently for various languages. This study focuses on Thai as a language that differs from English in terms of word combinations. We applied various automatic speech recognition (ASR) techniques to develop an assisted scoring system for the MoCA language fluency test with Thai language support. This was a challenge because Thai is a low-resource language for which domain-specific data are not publicly available, especially speech data from patients with MCIs. Furthermore, the great variety of pronunciation, intonation, tone, and accent of the patients, all of which might differ from healthy controls, bring more complexity to the model. We propose a hybrid time delay neural network hidden Markov model (TDNN-HMM) architecture for acoustic model training to create our ASR system that is robust to environmental noise and to the variation of voice quality impacted by MCI. The LOTUS Thai speech corpus was incorporated into the training set to improve the model’s generalization. A preprocessing algorithm was implemented to reduce the background noise and improve the overall data quality before feeding data into the TDNN-HMM system for automatic word detection and language fluency score calculation. The results show that the TDNN-HMM model in combination with data augmentation using lattice-free maximum mutual information (LF-MMI) objective function provides a word error rate (WER) of 30.77%. To our knowledge, this is the first study to develop an ASR with Thai language support to automate the scoring system of MoCA’s language fluency assessment.

The Montreal Cognitive Assessment (MoCA), a widely accepted screening tool for identifying patients with mild cognitive impairment (MCI), includes a language fluency test of verbal functioning where scores are based on the number of unique correct words produced by the test-taker. However, with different languages, it is possible that unique words may be counted differently. This study focuses on Thai as a language that differs from English in its type of word combination. We applied various automatic speech recognition (ASR) techniques to develop an assisted scoring system for the language fluency test of the MoCA with Thai language support. The extra challenge is that Thai is a low-resource language where domain-specific data are not publicly available, especially speech data from patients with MCI. We propose a hybrid Time Delay Neural Network - Hidden Markov Model (TDNN-HMM) architecture for acoustic model training to create our ASR system that is robust to environmental noise and the variation of voice quality impacted by MCI. The LOTUS Thai speech corpus is incorporated into the training set to improve the model’s generalization. A preprocessing algorithm is implemented to reduce the background noise and improve the overall data quality before feeding into the TDNN-HMM system for automatic word detection and language fluency score calculation. The results show that the TDNN-HMM model in combination with data augmentation using lattice-​free maximum mutual information (LF-MMI) objective function provides a word error rate (WER) of 41.30%. To our knowledge, this is the first study to develop an ASR with Thai language support to automate the scoring system of the MoCA’s language fluency assessment.