Automatic voice pathology detection is a research topic, which has gained increasing interest recently. Although methods based on deep learning are becoming popular, the classical pipeline systems based on a two-stage architecture consisting of a feature extraction stage and a classifier stage are still widely used. In these classical detection systems, frame-wise computation of mel-frequency cepstral coefficients (MFCCs) is the most popular feature extraction method. However, no systematic study has been conducted to investigate the effect of the MFCC frame length on automatic voice pathology detection. In this work, we studied the effect of the MFCC frame length in voice pathology detection using three disorders (hyperkinetic dysphonia, hypokinetic dysphonia and reflux laryngitis) from the Saarbrücken Voice Disorders (SVD) database. The detection performance was compared between speaker-dependent and speaker-independent scenarios as well as between speaking task -dependent and speaking task -independent scenarios. The Support Vector Machine, which is the most widely used classifier in the study area, was used as the classifier. The results show that the detection accuracy depended on the MFFC frame length in all the scenarios studied. The best detection accuracy was obtained by using a MFFC frame length of 500 ms with a shift of 5 ms.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.jvoice.2022.03.021 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Comprehensive discovery and functional characterization of the noncanonical proteome.
Cell Res
January 2025
The Center for RNA Medicine, International Institutes of Medicine, International School of Medicine, The 4th Affiliated Hospital of Zhejiang University School of Medicine, Yiwu, Zhejiang, China.
The systematic identification and functional characterization of noncanonical translation products, such as novel peptides, will facilitate the understanding of the human genome and provide new insights into cell biology. Here, we constructed a high-coverage peptide sequencing reference library with 11,668,944 open reading frames and employed an ultrafiltration tandem mass spectrometry assay to identify novel peptides. Through these methods, we discovered 8945 previously unannotated peptides from normal gastric tissues, gastric cancer tissues and cell lines, nearly half of which were derived from noncoding RNAs.
View Article and Find Full Text PDFRenal pelvis pressure and flowrate with a multi-channel ureteroscope: invoking the concept of outflow resistance.
Urolithiasis
January 2025
Department of Urology, University of Michigan, 1500 E. Medical Center Drive, Ann Arbor, MI, 48109-5330, USA.
Understanding renal pelvis pressure (P) during ureteroscopy (URS) has become increasingly important. High irrigation rates, desirable to maintain visualization and limit thermal dose, can increase P. Use of a multi-channel ureteroscope (m-ureteroscope) with a dedicated drainage channel is one strategy that may facilitate simultaneous low P and high flowrate.
View Article and Find Full Text PDFSTIPS algorithm enables tracking labyrinthine patterns and reveals distinct rhythmic dynamics of actin microridges.
Phys Biol
January 2025
Department of Biological Sciences, Tata Institute of Fundamental Research Department of Biological Sciences, Tata Institute of Fundamental Research, Homi Bhabha road, Navy Nagar, Colaba, Mumbai-400005, INDIA, Mumbai, 400005, INDIA.
Tracking and motion analyses of semi-flexible biopolymer networks from time-lapse microscopy images are important tools that enable quantitative measurements to unravel the dynamic and mechanical properties of biopolymers in living tissues, crucial for understanding their organization and function. Biopolymer networks are challenging to track due to continuous stochastic transitions, such as merges and splits, which cause local neighbourhood rearrangements over short time and length scales. To address this, we propose the STIPS algorithm (Spatio Temporal Information on Pixel Subsets) to track these events by creating pixel subsets that link trajectories across frames.
View Article and Find Full Text PDFFirst report of the whole‑genome sequence analysis of Fig badnavirus 2 from China.
Virus Genes
January 2025
College of Agronomy, Key Laboratory of Prevention and Control of Invasive Alien Species in Agriculture & Forestry of the North-Western Desert Oasis, Ministry of Agriculture and Rural Affairs, Xinjiang Agricultural University, Urumqi, 830052, China.
A novel plant virus was identified in fig trees exhibiting ring spot symptoms through high-throughput sequencing (HTS). The complete genome sequence was successfully determined using PCR and RT-PCR techniques. The virus features a circular DNA genome of 7233 nucleotides (nt) in length, encompassing four open reading frames (ORFs).
View Article and Find Full Text PDFInpatient Multimodal Pain Regimens Do Not Impact Hospital Length of Stay or Long-term Postoperative Opioid Use Following 1 and 2-Level Lumbar Fusion.
Clin Spine Surg
January 2025
Department of Orthopaedic Surgery, Rothman Orthopaedic Institute at Thomas Jefferson University, Philadelphia, PA.
Study Design: Retrospective cohort study.
Objective: To determine hospital length of stay (LOS) and long-term opioid consumption among patients who received inpatient multimodal analgesia following lumbar spine surgery, as opposed to those who received opioids alone.
Summary Of Background Data: Opioids have long been the historical choice for managing postoperative pain.
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!