Eurospeech 2001 - Scandinavia SPEAKER RECOGNITION BY SEPARATING PHONETIC SPACE AND SPEAKER SPACE
نویسندگان
چکیده
In speaker recognition, it is a problem that speech f e a-ture varies depending on sentences and time diierence. This variation is mainly attributed to the variation of phonetic information and speaker information included in speech data. If these two kinds of information are separated each other, robust speaker recognition will be realized. In this study, w e propose a speaker identiica-tion and speaker veriication method by separating the phonetic information and speaker information by a sub-space method, under the assumption that a space with large within-speaker variance is a \phonetic space" and a space with small within-speaker variance is a \speaker space". We carried out comparative experiments of the proposed method with a conventional method based on GMM in an observation space as well as in a space transformed by L D A. As a result, we could construct a robust speaker model with a few model parameters using a few training data by the proposed method.
منابع مشابه
Speaker recognition by separating phonetic space and speaker space
In speaker recognition, it is a problem that speech f e a-ture varies depending on sentences and time diierence. This variation is mainly attributed to the variation of phonetic information and speaker information included in speech data. If these two kinds of information are separated each other, robust speaker recognition will be realized. In this study, w e propose a speaker identiica-tion a...
متن کاملSpeaker adaptation by modeling the speaker variation in a continuous speech recognition system
A method for unsupervised instantaneous speaker adaptation is presented and evaluated on a continuous speech recognition task in a man-machine dialogue system. The method is based on modeling of the systematic speaker variation. The variation is modeled by a low-dimensional speaker space and the classification of speech segments is conditioned by the position in the speaker space. Because the e...
متن کاملEliminating Inter-speaker Variability Prior to Discriminant Transforms
This paper shows the impact of speaker normalization techniques such as vocal tract length normalization (VTLN) and speaker-adaptive training (SAT) prior to discriminant feature space transforms, such as LDA. We demonstrate that removing the inter-speaker variability by using speaker compensation methods results in improved discrimination as measured by the LDA eigenvalues and also in improved ...
متن کاملMixture input transformations for adaptation of hybrid connectionist speech recognizers
We extend the input transformation approach for adapting hybrid connectionist speech recognizers to allow multiple transformations to be trained. Previous work has shown the efficacy of the linear input transformation approach for speaker adaptation [1][2][3], but has focused only on training global transformations. This approach is clearly suboptimal since it assumes that a single transformati...
متن کاملSpeaker recognition based on feature space trace
This paper presents a multiple templates matching algorithm based on feature space trace, which is used in speaker recognition. It extracts the cepstrum coefficient as feature parameter. We normalize the sequence of feature parameter based on feature space trace. The fuzzy c-means method is adopted in generating the multiple templates and the multiple matching method is applied to match the tem...
متن کامل