搜索结果: 1-15 共查到“Speaker Verification”相关记录17条 . 查询时间(0.062 秒)
Speaker Verification Using Orthogonal GMM with Fusion of Threshold,Identification Front-end,and UBM
Speaker Verification Orthogonal GMM Fusion of Threshold Identification Front-end UBM
2015/9/29
This paper shows that the performance of a Gaussian Mixture Model using a Universal Background Model (GMM-UBM) speaker verification (SV) system can be further improved by combining it with threshold a...
Speaker Verification Over Handheld Devices with Realistic Noisy Speech Data
Handheld Devices Realistic Noisy Speech Data
2015/3/10
Speaker Verification Over Handheld Devices with Realistic Noisy Speech Data.
The MIT Mobile Device Speaker Verification Corpus: Data collection and preliminary experiments
Data collection preliminary experiments
2015/3/10
The MIT Mobile Device Speaker Verification Corpus: Data collection and preliminary experiments.
Unsupervised Speaker Adaptation Based on the Cosine Similarity for Text-Independent Speaker Verification
Cosine Similarity Text-Independent Speaker Verification
2015/3/10
Unsupervised Speaker Adaptation Based on the Cosine Similarity for Text-Independent Speaker Verification.
A Channel-Blind System for Speaker Verification.
Front-End Factor Analysis for Speaker Verification
Cosine distance scoring joint factor analysis
2015/3/9
Front-End Factor Analysis for Speaker Verification.
First Attempt of Boltzmann Machines for Speaker Verification
Boltzmann Machines Speaker Verification
2015/3/9
Frequently organized by NIST1
, Speaker Recognition
evaluations (SRE) show high accuracy rates. This
demonstrates that this field of research is mature. The
latest progresses came from the prop...
Bayesian Distance Metric Learning on i-vector for Speaker Verification
i-vector score normalization
2015/3/9
Bayesian Distance Metric Learning on i-vector for Speaker Verification.
New Cosine Similarity Scorings to Implement Gender-independent Speaker Verification
Speaker verification Cosine similarity
2015/3/9
New Cosine Similarity Scorings to Implement Gender-independent Speaker Verification.
Bayesian Distance Metric Learning on i-vector for Speaker Verification
i-vector score normalization distance metric learning channel compensation limited training utterances
2014/11/27
This paper presents a new speaker verification system based on i-vector modeling as a feature extractor. In this modeling, we explore the distance constraints between i-vector pairs from the same spea...
Unsupervised Speaker Adaptation based on the Cosine Similarity for Text-Independent Speaker Verification
Unsupervised Speaker Adaptation Cosine Similarity Text-Independent Speaker Verification
2014/11/27
This paper proposes a new approach to unsupervised speaker adaptation inspired by the recent success of the factor analysisbased Total Variability Approach to text-independent speaker verification [1]...
SPEAKER VERIFICATION OVER HANDHELD DEVICES WITH REALISTIC NOISY SPEECH DATA
SPEAKER VERIFICATION HANDHELD DEVICES REALISTIC NOISY SPEECH DATA
2014/11/27
We study speaker verification f or handheld devices assuming realistic, noisy test conditions and assuming no prior knowledge of the noise characteristics. Data were r ecorded in office ( “quiet”) and...
GMM Weights Adaptation Based on Subspace Approaches for Speaker Verification
Subspace Approaches Speaker Verification
2015/3/9
GMM Weights Adaptation Based on Subspace Approaches for Speaker Verification.
Using Phoneme Recognition and Text-dependent Speaker Verification to Improve Speaker Segmentation for Chinese Speech
speaker segmentation phoneme recognition text-dependent short utterances
2013/6/28
Speaker segmentation is widely used in many tasks such as multi-speaker detection and speaker tracking. The segmentation performance depends on the performance of
speaker verification (SV) between t...
A Cohort-Based Speaker Model Synthesis for Mismatched Channels in Speaker Verification
Channel mismatch cohort speaker model syn-thesis speaker verification
2013/6/28
Mismatch between enrollment and test data is one of the top performance degrading factors in speaker recognition applications. This mismatch is particularly true over public telephone networks, where ...