Results 91 to 100 of about 8,304 (223)
OVERCOMING OVERFITTING IN MONKEY VOCALIZATION CLASSIFICATION: USING LSTM AND LOGISTIC REGRESSION
BarekengThe problem of overfitting in a classification task involving animal vocalizations, namely squirrel monkeys, golden lion tamarins, and tailed macaques, is handled in this project.
Suryasatriya Trihandaru +2 more
doaj +1 more source
Confusion matrix [%] using IEMOCAP and DNN with MFCC/SDC features.
, 2019 Confusion matrix [%] using IEMOCAP and DNN with MFCC/SDC features.
Panikos Heracleous (7251320) +1 more
core +1 more source
Reconstructing clean speech from noisy MFCC vectors
, 2009 The aim of this work is to reconstruct clean speech solely from a stream of noise-contaminated MFCC vectors, as may be encountered in distributed speech recognition systems.
Darch, Jonathan +5 more
core
Confusion matrix [%] using IEMOCAP and CNN with MFCC/SDC features.
, 2019 Confusion matrix [%] using IEMOCAP and CNN with MFCC/SDC features.
Panikos Heracleous (7251320) +1 more
core +1 more source
Analisis Variasi Jumlah Fitur MFCC pada LSTM dalam Klasifikasi Suara Aksen Berbahasa Inggris
, 2022 Numerous research have been performed to classify English accents using both classic and contemporary classification methods. In general, past research on voice classification and voice recognition employs the MFCC approach to extract voice features ...
Sharif, Afriandy
core
피치히스토그램과 MFCC-VQ 동적패턴을 이용한 음악 검색
, 2005 학위논문(석사) - 한국정보통신대학교 : 공학부, 2005, [ x, 43 p. ]When we listen to unknown music contents on TV or computer, we often want to know some information about the music.
박철의, Park, Chul-Eui
core
Accuracy (%) by using original DTW on different (non)normalized dimensional MFCC.
, 2014 In the first column, numbers represent dimensions, ‘Norm’ means normalized MFCC, and ‘NonNorm’ means unnormalized MFCC.
Jiping Sun (521543) +2 more
core +1 more source
Automatic Speech Recognition and Verification using LPC, MFCC and SVM
, 2015 Speech has much capability as an interface between human and computer which comes under the Human Computer interaction (HCI). The major challenge has been the nature of voice is ever varying speech signal. The paper presents the development of the speech
Janvale, Ganesh B. +2 more
core
Dianxin kexue为了充分挖掘语音信号频谱包含的情感信息以提高语音情感识别的准确性，提出了一种基于小波散射变换和梅尔频率倒谱系数（Mel-frequency cepstral coefficient，MFCC）的排列熵加权和偏差调整规则的语音情感识别融合算法（PEW-BAR）。算法首先获取语音信号的小波散射特征和梅尔频率倒谱系数的相关特征；然后按尺度维度扩展小波散射特征，利用支持向量机得到情感识别的后验概率并获得排列熵，并使用排列熵对后验概率进行加权；最后采用一种偏差调整规则进一步融合MFCC的相关特征的识别结果 ...
应娜, 吴顺朋, 杨萌, 邹雨鉴
doaj +1 more source
Computing nasalance with MFCCs and Convolutional Neural Networks
PLOS ONENasalance is a valuable clinical biomarker for hypernasality. It is computed as the ratio of acoustic energy emitted through the nose to the total energy emitted through the mouth and nose (eNasalance). A new approach is proposed to compute nasalance using Convolutional Neural Networks (CNNs) trained with Mel-Frequency Cepstrum Coefficients ...
Andrés Lozano +3 more
openaire +3 more sources