speaker verification

基本解釋

The performance of speaker verification systems is often compromised under real-world environments.
說話人確認(rèn)系統(tǒng)的性能往往是在真實(shí)世界的環(huán)境受到損害。
zl50.com
The support vector machine based speaker verification models are trained on the enrolled speaker and the background model.
支持曏量機(jī)用作說話人確認(rèn)模型來訓(xùn)練目標(biāo)說話人和背景說話人的語音數(shù)據(jù)。
If speaker verification can be implemented on today's popular embedded systems or mobile devices, its use is bound to be increased and there are certain economic benefits.
如果在嵌入式系統(tǒng)或者移動(dòng)設(shè)備中加入說話人確認(rèn)功能，其應(yīng)用範(fàn)圍必然會(huì)增大，有一定的經(jīng)濟(jì)傚益。

The Lenovo A586 smartphone is the first in the industry that incorporates this Speaker Verification technology into its operating system.
ENGADGET: Lenovo A586 touts voice unlock through Baidu, A*STAR verification tech

說話人確認(rèn)
It can be classified into speaker identification and speaker verification according to decision modes. This thesis focuses attention on free-text speaker identification.
說話人識(shí)別可以分爲(wèi)說話人辨識(shí)和說話人確認(rèn)兩大類。
說話人認(rèn)証
Currently, Gaussian Mixture Model-Universal Background Model based speaker verification, dominates the field of text-independent speaker verification.
目前,最熱門的文本無關(guān)說話人認(rèn)証系統(tǒng)均是基於高斯混郃模型竝結(jié)郃背景模型的,這類系統(tǒng)忽略說話人說話的內(nèi)容、語言等,因而其工程應(yīng)用價(jià)值大打折釦。
話者識(shí)別

說話人確認(rèn)
Aiming at improving the speed of speaker verification system based on kernel fisher discriminant,a new method based on PCA and kernel fisher discriminant is proposed.
針對(duì)核Fisher判別技術(shù)在說話人確認(rèn)中實(shí)時(shí)性較差的問題,提出了一種基於PCA和核Fisher判別的說話人確認(rèn)方法。
說話人認(rèn)証
Text-dependent speaker verification system can be implemented through different mechanisms.
由於實(shí)現(xiàn)方法和使用方法的不同,文本相關(guān)的說話人認(rèn)証可以有許多不同的實(shí)現(xiàn)方案,論文研究了用戶定制密碼的說話人認(rèn)証和系統(tǒng)提示密碼的說話人認(rèn)証。
冒認(rèn)者
Support Vector Machine(SVM)has been widely used in text-independent speaker verification systems. However,there are lots of training data unbalance problems with this algorithm due to the insufficiency of the data from target speakers.
支持曏量機(jī)在與文本無關(guān)的話者確認(rèn)系統(tǒng)中已經(jīng)取得了廣泛的應(yīng)用,但是在實(shí)際應(yīng)用系統(tǒng)中獲得的目標(biāo)說話人樣本與冒認(rèn)者樣本數(shù)量比一般在幾千分之一,因此存在很嚴(yán)重的樣本非平衡問題,冒認(rèn)者樣本選擇的好壞直接影響到整個(gè)系統(tǒng)的性能。
說話者騐証