Discrimination Effectiveness of Speech Cepstral Features

Malegaonkar, A.; Ariyaeeinia, Aladdin M.; Sivakumaran, P.; Pillay, S.

doi:10.1007/978-3-540-89991-4_10

Cited by 3 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…That is to calculate the difference between UBM log-likelihood and speaker's loglikelihood as an evaluation criterion. Malegaonka considered that this is a unilateral scoring (ULS) [113,114]. That is, when the models built using speech from a speaker (speaker A) are matched against speech from another speaker (speaker B), they may not return high likelihoods whilst speech from speaker A matched against the models built using speech from speaker B giving high likelihoods.…”

Section: Better Algorithms For Scoringmentioning

confidence: 99%

An overview of robustness related issues in speaker recognition

Zheng¹,

Jin

Li³

et al. 2014

Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific

View full text Add to dashboard Cite

Speaker recognition technologies have been improved rapidly in recent years. However, critical robustness issues need to be addressed when they are applied in practical situations. This paper provides an overview of technologies dealing with robustness related issues in automatic speaker recognition. We first categorize the robustness issues into three categories, including environment-related, speaker-related and application-oriented issues. For each category, we then describe the current hot topics, existing technologies, and potential research focuses in the future.I.

show abstract

Section: Better Algorithms For Scoringmentioning

confidence: 99%