This paper reports the findings of an automatic dialect identification (DID) task conducted on Ao speech data using source features. Considering that Ao is a tone language, in this study for DID, the gammatonegram of the linear prediction residual is proposed as a feature. As Ao is an under-resourced language, data augmentation was carried out to increase the size of the speech corpus. The results showed that data augmentation improved DID by 14%. A perception test conducted on Ao speakers showed better DID by the subjects when utterance duration was 3 s. Accordingly, automatic DID was conducted on utterances of various duration. A baseline DID system with the S feature attained an average F1-score of 53.84% in a 3 s long utterance. Inclusion of source features, S and , improved the F1-score to 60.69%. In a final system, with a combination of S, , S, and Mel frequency cepstral coefficient features, the F1-score increased to 61.46%.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1121/10.0014176 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Improving Access to Early Developmental Evaluation in Academic Primary Care Centers.
Pediatr Qual Saf
January 2025
Division of Developmental and Behavioral Pediatrics, Cincinnati Children's Hospital Medical Center, University of Cincinnati College of Medicine, Cincinnati, OHIO.
Introduction: Developmental disorders (DDs) affect approximately 1 in 6 children in the United States. Early identification and treatment improve developmental outcomes and child and family functioning. Disparities exist in the diagnosis of DD that leads to inequitable access to developmental services during important periods of neuroplasticity.
View Article and Find Full Text PDFAdvancements in Ultrasound Diagnosis of Superficial Endometriosis: Current Challenges and Emerging Techniques.
Gynecol Obstet Invest
January 2025
Background: Endometriosis is a chronic disease characterized by endometrial-like tissue outside the uterus. Superficial endometriosis (SE) is the most prevalent form, yet it remains underdiagnosed due to subtle clinical and imaging presentations. Traditionally, diagnosis relies on laparoscopy, which is relatively invasive and often contributes to diagnostic delay.
View Article and Find Full Text PDFUtilizing natural language processing to identify pediatric patients experiencing status epilepticus.
Seizure
January 2025
Division of Epilepsy and Clinical Neurophysiology, Boston Children's Hospital, Harvard Medical School, 300 Longwood Ave, Boston, MA 02115, USA.
Purpose: Compare the identification of patients with established status epilepticus (ESE) and refractory status epilepticus (RSE) in electronic health records (EHR) using human review versus natural language processing (NLP) assisted review.
Methods: We reviewed EHRs of patients aged 1 month to 21 years from Boston Children's Hospital (BCH). We included all patients with convulsive ESE or RSE during admission.
Identification of cardiac wall motion abnormalities in diverse populations by deep learning of the electrocardiogram.
NPJ Digit Med
January 2025
Department of Medicine, Stanford University School of Medicine, Stanford, CA, USA.
Cardiac wall motion abnormalities (WMA) are strong predictors of mortality, but current screening methods using Q waves from electrocardiograms (ECGs) have limited accuracy and vary across racial and ethnic groups. This study aimed to identify novel ECG features using deep learning to enhance WMA detection, referencing echocardiography as the gold standard. We collected ECG and echocardiogram data from 35,210 patients in California and labeled WMA using unstructured language parsing of echocardiographic reports.
View Article and Find Full Text PDFSP-DTI: Subpocket-Informed Transformer for Drug-Target Interaction Prediction.
Bioinformatics
January 2025
School of Engineering, Westlake University, Hangzhou, 310024, China.
Motivation: Drug-target interaction (DTI) prediction is crucial for drug discovery, significantly reducing costs and time in experimental searches across vast drug compound spaces. While deep learning has advanced DTI prediction accuracy, challenges remain: (i) existing methods often lack generalizability, with performance dropping significantly on unseen proteins and cross-domain settings; (ii) current molecular relational learning often overlooks subpocket-level interactions, which are vital for a detailed understanding of binding sites.
Results: We introduce SP-DTI, a subpocket-informed transformer model designed to address these challenges through: (i) detailed subpocket analysis using the Cavity Identification and Analysis Routine (CAVIAR) for interaction modeling at both global and local levels, and (ii) integration of pre-trained language models into graph neural networks to encode drugs and proteins, enhancing generalizability to unlabeled data.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!