Latent Prosody Analysis for Robust Speaker Identification

Liao, Yuan-Fu; Chen, Zi-He; Juang, Yau-Tarng

doi:10.1109/tasl.2007.896660

Cited by 4 publications

(1 citation statement)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Individuals have their own style of speaking, depending on many factors like emotion, dialect and accent of the speech. Due to prosody of the language, speaker identification also becomes challenging task [3]. This paper focuses on automatically identifying the emotion of a speaker given a sample of speech and demonstrates how such a technology can be employed to improve the Recognition system.…”

Section: Introductionmentioning

confidence: 99%

Text independent emotion recognition for Telugu speech by using prosodic features

Mannepalli¹,

Maloji²,

Sastry³

et al. 2018

IJET

View full text Add to dashboard Cite

The human speech delivers different types of information about the speaker and speech. From the speech production side, the speech signal carries linguistic information such as the meaningful message and the language and emotional, geographical and the speaker's physiological characteristics of the speaker information are conveyed. This paper focuses on automatically identifying the emotion of a speaker given a sample of speech. the speech signals considered in this work are collected from Telugu speakers. The features like pitch, pitch related prosody, energy and formants. The overall recognition accuracy obtained is 72% in this work.

show abstract

Section: Introductionmentioning

confidence: 99%