Results 91 to 100 of about 3,610,992 (210)
Inter‐Model Feature Fusion for Robust Low‐Resource Speech Recognition
Applied AI Letters, Volume 7, Issue 2, June 2026.Our Self‐Supervised Feature Fusion (SSF‐FT) method enhances low‐resource speech recognition by adaptively combining features from self‐supervised models trained with Contrastive, Predictive, and Reconstruction objectives. This attention‐weighted ensemble delivers robust performance, particularly in acoustically challenging conditions, extending current
Ussen Kimanuka +2 more
wiley +1 more source
On Compensating the Mel-Frequency Cepstral Coefficients
, 2008 This paper describes a novel noise-robust automatic speech recognition (ASR) front-end that employs a combination of Mel-filterbank output compensation and cumulative distribution mapping of cepstral coefficients with truncated Gaussian distribution ...
For Noisy Speech, Eric H. C. Choi
core
Application of Music Data Visualization Technology in Music Appreciation Teaching
Engineering Reports, Volume 8, Issue 6, June 2026.The simulation environment is used to simulate real‐world music appreciation scenarios. DL is employed to preprocess music data, extract features, and identify rhythm information, which is then associated with visual design parameters to construct a parametric model.
Xiaowei Chen
wiley +1 more source
Results in EngineeringKnocking-sound analysis provides a non-destructive method for assessing durian ripeness; however, most convolutional neural network methods mainly emphasize magnitude information while disregarding phase information that reflects the overall signal ...
Khomdet Phapatanaburi +7 more
doaj +1 more source
Automated classification of vowel category and speaker type in the high-frequency spectrum
Audiology Research, 2016 The high-frequency region of vowel signals (above the third formant or F3) has received little research attention. Recent evidence, however, has documented the perceptual utility of high-frequency information in the speech signal above the traditional ...
Jeremy J. Donai +2 more
doaj +1 more source
Medycyna Pracy, 2013 Background: Special consideration has recently been given to cepstral analysis with mel-frequency cepstral coefficients (MFCCs). The aim of this study was to assess the applicability of MFCCs in acoustic analysis for diagnosing occupational dysphonia in ...
Ewa Niebudek-Bogusz +3 more
doaj +1 more source
Use of Mel Frequency Cepstral Coefficients for Automatic Pathology Detection on Sustained Vowel Phonations: Mathematical and Statistical Justification [PDF]
, 2008 This paper presents a justification for the use of MFCC parameters in automatic pathology detection on speech. While such an application has produced good results up to now, only partial explanations to this good performance had been given before.
Sáenz Lechón, Nicolas +4 more
core
Cepstral Coefficients Effectiveness for Gunshot Classifying [PDF]
This paper analyses the efficiency of various frequency cepstral coefficients (fCC) in a non-speech application, specifically in classifying acoustic impulse events - gunshots. There are various methods for such event identification available.
Holub J., Svatoš J.
core +1 more source
, 2017 Identification of voice signals can be used to command a computer system. Identification can be made of voice owner and spoken word. Identification of voice owner is used for security, while spoken word identification is often used to execute command on ...
Munggaran, Angga Kersana +2 more
core
Multilingual Speaker Identification by Combining Evidence from LPR and Multitaper MFCC
Journal of Intelligent Systems, 2013 In this work, the significance of combining the evidence from multitaper mel-frequency cepstral coefficients (MFCC), linear prediction residual (LPR), and linear prediction residual phase (LPRP) features for multilingual speaker identification with the ...
Nagaraja B.G., Jayanna H.S.
doaj +1 more source