Speaker verification score normalization using speaker model clusters

Apsingekar, Vijendra Raj; León, Phillip L. De

doi:10.1016/j.specom.2010.07.001

Cited by 11 publications

(9 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Step 1: Data Preprocessing. To eliminate difference between sensor data of different measurement standards, Zscore normalization is performed on the raw data [33]. Meanwhile, there are so many factors which influence on dissolved oxygen.…”

Section: The Hybrid Prediction Model Based On K-means and Iga-elmmentioning

confidence: 99%

An Enhanced Extreme Learning Machine for Dissolved Oxygen Prediction in Wireless Sensor Networks

Kuang¹,

Shi

Hua³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Water quality monitoring using Wireless Sensor Networks (WSNs) is essential in aquaculture water quality management. In the field of water quality monitoring, dissolved oxygen (DO) is a key parameter, and its prediction can provide decision support for aquaculture production, thereby reducing farming risk. However, it is difficult to build a precise prediction model, and existing methods of DO prediction neglect the importance of analyzing DO content. To address this problem, this study proposes a hybrid DO prediction model, named KIG-ELM, which is composed of K-means, improved genetic algorithm (IGA), and extreme learning machine (ELM). This model is based on edge computing architecture, in which data acquisition, processing and dissolved oxygen prediction are distributed in sensing nodes, routing nodes and server respectively. Sensing technique and clustering operation are applied in the process of data acquisition and processing. Meanwhile, an optimized extreme learning machine is implemented for DO prediction. We evaluate the efficiency and accuracy of proposed prediction approach in a practical aquaculture on massive water quality data. Experimental results show that the hybrid model achieves significant prediction results and can meet the needs of practical production and management.

show abstract

Section: The Hybrid Prediction Model Based On K-means and Iga-elmmentioning

confidence: 99%

An Enhanced Extreme Learning Machine for Dissolved Oxygen Prediction in Wireless Sensor Networks

Kuang¹,

Shi

Hua³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…For each target, the nearest Tnorm impostors are chosen to normalize the scores. A different approach which performs k-means clustering in order to select a subset of impostors for Z-norm and T-norm is proposed in [2].…”

Section: Score Normalization Techniquesmentioning

confidence: 99%

“…In [2], the cohort selection is performed by using k-means to cluster the normalization models and choosing the nearest cluster to the target model. However this approach is proposed for text-independent speaker verification, where the target and normalization models are trained with different lexical contents of the enrolment data.…”

Section: Cohort Selection For Text-dependent Speaker Verificatiomentioning

confidence: 99%

Cohort selection for text-dependent speaker verification score normalization

Khemiri

Petrovska‐Delacrétaz

2016

2016 2nd International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)

View full text Add to dashboard Cite

Subspace based techniques, such as i-vector and Joint Factor Analysis (JFA) have shown to provide state-of-the-art performance for fixed phrase based text-dependent speaker verification. However, the error rates of such systems on the random digit task of RSR dataset are higher than that of Gaussian Mixture Model-Universal Background Model (GMM-UBM). In this paper, we aim at improving i-vector system by normalizing the content of the enrollment data to match the test data. We estimate i-vectors for each frames of a speech utterance (also called online i-vectors). The largest similarity scores across frames between enrollment and test are taken using these online i-vectors to obtain speaker verification scores. Experiments on Part3 of RSR corpora show that the proposed approach achieves 12% relative improvement in equal error rate over a GMM-UBM based baseline system.

show abstract

“…The shifts and scales are usually estimated using a set of utterances so called normalization cohort. It has been shown many times that for GMM-UBM algorithms [4,1] and later especially for Joint Factor Analysis (JFA) based system [5,6], we might achieve significantly better accuracy with score normalization, such as Z-norm [4], T-norm [7], combinations of both (TZ-norm and ZTnorm) [8] or other variants such as H-norm [1], D-norm [9], KL-T-norm [10], S-norm [11], normalized cosine similarity [12], speaker clusters [13] and many others [14,15,16].…”

Section: Introductionmentioning

confidence: 99%

Analysis of Score Normalization in Multilingual Speaker Recognition

Matějka¹,

Novotny²,

Plchot³

et al. 2017

Interspeech 2017

View full text Add to dashboard Cite

NIST Speaker Recognition Evaluation 2016 has revealed the importance of score normalization for mismatched data conditions. This paper analyzes several score normalization techniques for test conditions with multiple languages. The best performing one for a PLDA classifier is an adaptive s-norm with 30% relative improvement over the system without any score normalization. The analysis shows that the adaptive score normalization (using top scoring files per trial) selects cohorts that in 68% contain recordings from the same language and in 92% of the same gender as the enrollment and test recordings. Our results suggest that the data to select score normalization cohorts should be a pool of several languages and channels and if possible, its subset should contain data from the target domain.

show abstract

Speaker verification score normalization using speaker model clusters

Cited by 11 publications

References 15 publications

An Enhanced Extreme Learning Machine for Dissolved Oxygen Prediction in Wireless Sensor Networks

An Enhanced Extreme Learning Machine for Dissolved Oxygen Prediction in Wireless Sensor Networks

Cohort selection for text-dependent speaker verification score normalization

Analysis of Score Normalization in Multilingual Speaker Recognition

Contact Info

Product

Resources

About