The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
본 논문에서는 두 가지 새로운 특징인 상관 밀도(correlation Density)를 사용하는 새로운 방법을 제안합니다.Cd) 및 프랙탈 차원(Fd), 음성에 포함된 감정 상태를 인식합니다. 파라메트릭 필터 목록에서 얻은 전자의 특징은 무성 전화기와 유성 전화기 각각에 의해 기여된 넓은 주파수 성분과 저주파 성분의 미세 구조를 반영합니다. 후자의 특징은 음성 신호의 비선형성과 자기 유사성을 나타냅니다. Hidden Markov Model과 K Nearest Neighbor 방법을 기반으로 한 비교 실험을 수행한다. 결과는 Cd and Fd 일반적으로 사용되는 기능보다 감정 표현과 훨씬 더 밀접하게 관련되어 있습니다.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Xia MAO, Lijiang CHEN, "Speech Emotion Recognition Based on Parametric Filter and Fractal Dimension" in IEICE TRANSACTIONS on Information,
vol. E93-D, no. 8, pp. 2324-2326, August 2010, doi: 10.1587/transinf.E93.D.2324.
Abstract: In this paper, we propose a new method that employs two novel features, correlation density (Cd) and fractal dimension (Fd), to recognize emotional states contained in speech. The former feature obtained by a list of parametric filters reflects the broad frequency components and the fine structure of lower frequency components, contributed by unvoiced phones and voiced phones, respectively; the latter feature indicates the non-linearity and self-similarity of a speech signal. Comparative experiments based on Hidden Markov Model and K Nearest Neighbor methods are carried out. The results show that Cd and Fd are much more closely related with emotional expression than the features commonly used.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E93.D.2324/_p
부
@ARTICLE{e93-d_8_2324,
author={Xia MAO, Lijiang CHEN, },
journal={IEICE TRANSACTIONS on Information},
title={Speech Emotion Recognition Based on Parametric Filter and Fractal Dimension},
year={2010},
volume={E93-D},
number={8},
pages={2324-2326},
abstract={In this paper, we propose a new method that employs two novel features, correlation density (Cd) and fractal dimension (Fd), to recognize emotional states contained in speech. The former feature obtained by a list of parametric filters reflects the broad frequency components and the fine structure of lower frequency components, contributed by unvoiced phones and voiced phones, respectively; the latter feature indicates the non-linearity and self-similarity of a speech signal. Comparative experiments based on Hidden Markov Model and K Nearest Neighbor methods are carried out. The results show that Cd and Fd are much more closely related with emotional expression than the features commonly used.},
keywords={},
doi={10.1587/transinf.E93.D.2324},
ISSN={1745-1361},
month={August},}
부
TY - JOUR
TI - Speech Emotion Recognition Based on Parametric Filter and Fractal Dimension
T2 - IEICE TRANSACTIONS on Information
SP - 2324
EP - 2326
AU - Xia MAO
AU - Lijiang CHEN
PY - 2010
DO - 10.1587/transinf.E93.D.2324
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E93-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2010
AB - In this paper, we propose a new method that employs two novel features, correlation density (Cd) and fractal dimension (Fd), to recognize emotional states contained in speech. The former feature obtained by a list of parametric filters reflects the broad frequency components and the fine structure of lower frequency components, contributed by unvoiced phones and voiced phones, respectively; the latter feature indicates the non-linearity and self-similarity of a speech signal. Comparative experiments based on Hidden Markov Model and K Nearest Neighbor methods are carried out. The results show that Cd and Fd are much more closely related with emotional expression than the features commonly used.
ER -