Deep-Learning-Based Segmentation of Predefined Chunks in Connected Speech: A Retrospective Analysis

Background and Objectives@#In institutional settings, manually segmenting connected speech is a time-consuming and labor-intensive process. This study aims to develop a deep-learning model for automating this process, evaluating its accuracy, and determining the minimum dataset size for effective performance.Materials and Method Voice data from 524 individuals with pathological conditions and 502 individuals with normal conditions, totaling 1026 samples, were used. Each voice sample had 17 chunks, including a “summer” sentence (15 chunks) and vowels /α/ and /i/. The deep-learning model employed in this study is based on the multi-layer perceptron-mixer architecture. This study evaluated performance using the Intersection over Union (IoU) metric, commonly employed in artificial intelligence-based image detection for chunk segmentation. @*Results@#The accuracy of chunk identification at the frame level was 96.47%. Using IoU metrics, chunk segmentation accuracy was 98.15% at IoU ≥0.6, 96.03% at IoU ≥0.7, and 89.78% at IoU ≥0.8. Optimal dataset size exploration indicated that more than 700 connected speech datasets were needed for successful training, maintaining F1-scores up to 95% at IoU ≥0.7. @*Conclusion@#The artificial intelligence model is suitable for the development of an automated system that efficiently divides segments in the institutional collection of voice data. This suggests its potential utility in advancing voice research using connected speech.

Prevalence of Toxoplasma gondii Infection in Stray and Household Cats in Regions of Seoul, Korea

The principal objective of this study was to investigate the prevalence of toxoplasmosis in household and stray cats in Seoul, Republic of Korea. We collected blood samples from 72 stray and 80 household cats, and all samples were examined by ELISA and nested PCR. The overall positive rates of Toxoplasma gondii in stray cats were 38.9% (28/72), with 15.3% (11/72) in ELISA and 30.6% (22/72) in PCR. The positive rate in male stray cats was slightly higher than that of female stray cats. The highest positive rate of T. gondii infection was noted in Gangnam and Songpa populations in ELISA and in Gwangjin population in PCR. In household cats, however, we could not detect any specific antibodies or DNA for T. gondii. In conclusion, we recognized that the infection rate of toxoplasmosis in stray cats in Seoul was considerably high but household cats were free from infection.