Comparison of multiple features and modeling methods for text-dependent speaker verification

Liu, Yi; He, Liang; Tian, Yanling; Chen, Zhuzi; Liu, Jia; Johnson, Michael T.

doi:10.1109/asru.2017.8268995

Cited by 12 publications

(2 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The FB alignment, which can be seen as a soft version of the Viterbi algorithm, computes the posterior from forward and backward probabilities [14]. In [15], it was shown that these two types of alignments result in similar performance. To better compare the alignments generated by HMM and DNN, the soft FB alignment is used in our experiments.…”

Section: The Role Of Hmmmentioning

confidence: 99%

Investigation of Frame Alignments for GMM-based Digit-prompted Speaker Verification

Liu

Zhang

et al. 2018

2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)

Self Cite

View full text Add to dashboard Cite

Frame alignments can be computed by different methods in GMM-based speaker verification. By incorporating a phonetic Gaussian mixture model (PGMM), we are able to compare the performance using alignments extracted from the deep neural networks (DNN) and the conventional hidden Markov model (HMM) in digit-prompted speaker verification. Based on the different characteristics of these two alignments, we present a novel content verification method to improve the system security without much computational overhead. Our experiments on the RSR2015 Part-3 digit-prompted task show that, the DNNbased alignment performs on par with the HMM alignment. The results also demonstrate the effectiveness of the proposed Kullback-Leibler (KL) divergence based scoring to reject speech with incorrect pass-phrases.

show abstract

Section: The Role Of Hmmmentioning

confidence: 99%

Investigation of Frame Alignments for GMM-based Digit-prompted Speaker Verification

Liu

Zhang

et al. 2018

2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)

Self Cite

View full text Add to dashboard Cite

show abstract

“…In text-dependent SV, utterance verification can be seen as a subtask. A comparison of different features and modeling techniques for text-dependent SV can be found in [24]. Joint speaker and utterance models with HMM triphone models are used in [25].…”

Section: Introductionmentioning

confidence: 99%

A Unified Framework for Speaker and Utterance Verification

Liu¹,

Madhavi

Das

et al. 2019

Interspeech 2019

View full text Add to dashboard Cite

Speaker and utterance verification are two tasks that co-exist in text-dependent speaker verification (SV), where a phrase of the same lexical information is spoken during train and test sessions. The conventional approaches mostly verify the speaker and the utterance separately using two models. While there are studies on joint modeling of speaker and utterance, it is always desirable to have a common framework that performs both speaker and utterance verification to access the intended service. To this end, we propose a unified framework that deals with both objectives and the trade-off between the two. The unified framework is based on long short term memory network trained using both speaker and utterance information. We use Part I of RSR2015 database for the studies in this work. We show that the unified framework not only demonstrates competitive SV performance, but also provides a solution for a system to address different levels of security need.

show abstract