Fast scoring for PLDA with uncertainty propagation via i-vector grouping

Lin, Weiwei; Mak, Man‐Wai; Chien, Jen‐Tzung

doi:10.1016/j.csl.2017.02.009

Cited by 20 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…assuming long training and enrollment utterances). The authors in [25], [26] speed-up the uncertainty propagation method by grouping i-vectors together based on their reliability and by finding a representative posterior covariance matrix for each group. In [27], the authors incorporate the uncertainty associated with front-end features into the i-vector extraction framework.…”

Section: B Modelling I-vector Uncertaintymentioning

confidence: 99%

Speaker Recognition With Random Digit Strings Using Uncertainty Normalized HMM-Based i-Vectors

Maghsoodi

Sameti

Zeinali

et al. 2019

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

In this paper, we combine Hidden Markov Models (HMMs) with i-vector extractors to address the problem of textdependent speaker recognition with random digit strings. We employ digit-specific HMMs to segment the utterances into digits, to perform frame alignment to HMM states and to extract Baum-Welch statistics. By making use of the natural partition of input features into digits, we train digit-specific i-vector extractors on top of each HMM and we extract well-localized i-vectors, each modelling merely the phonetic content corresponding to a single digit. We then examine ways to perform channel and uncertainty compensation, and we propose a novel method for using the uncertainty in the i-vector estimates. The experiments on RSR2015 part III show that the proposed method attains 1.52% and 1.77% Equal Error Rate (EER) for male and female respectively, outperforming state-of-the-art methods such as xvectors, trained on vast amounts of data. Furthermore, these results are attained by a single system trained entirely on RSR2015, and by a simple score-normalized cosine distance. Moreover, we show that the omission of channel compensation yields only a minor degradation in performance, meaning that the system attains state-of-the-art results even without recordings from multiple handsets per speaker for training or enrolment. Similar conclusions are drawn from our experiments on the RedDots corpus, where the same method is evaluated on phrases. Finally, we report results with bottleneck features and show that further improvement is attained when fusing them with spectral features.

show abstract

Section: B Modelling I-vector Uncertaintymentioning

confidence: 99%

Speaker Recognition With Random Digit Strings Using Uncertainty Normalized HMM-Based i-Vectors

Maghsoodi

Sameti

Zeinali

et al. 2019

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

show abstract

“…The authors considered the i-vector computation in (2) as a deterministic operation and consequently derived the i-vector as (15) where Nunc(u) is a diagonal matrix with blocks Nunc,c(u)I, Func(u) is the concatenation of Func,c(u), and the unbiased BW statistics [6] are given by γunc,t(c) = πc N (ȳt|µc, Σunc,c,t)…”

Section: Uncertainty Propagation Through the Ubmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…Other work based on the aleatoric uncertainty concept has also given rise to uncertainty propagation approaches for speaker recognition. However, these approaches focused on the issue of computing representations with in-sufficient data, caused by utterances with different, possibly short durations [9][10][11][12][13][14][15]. This paper pursues the same line as our preliminary study [8], that considered an epistemic uncertainty propagation approach for noise-robust text-independent speaker verification using a system based on i-vectors [16] and probabilistic linear discriminant analysis (PLDA) [17].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Improved Uncertainty Propagation Method for Robust I-vector Based Speaker Recognition

Ribas

2019

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

The performance of automatic speaker recognition systems degrades when facing distorted speech data containing additive noise and/or reverberation. Statistical uncertainty propagation has been introduced as a promising paradigm to address this challenge. So far, different uncertainty propagation methods have been proposed to compensate noise and reverberation in i-vectors in the context of speaker recognition. They have achieved promising results on small datasets such as YOHO and Wall Street Journal, but little or no improvement on the larger, highly variable NIST Speaker Recognition Evaluation (SRE) corpus. In this paper, we propose a complete uncertainty propagation method, whereby we model the effect of uncertainty both in the computation of unbiased Baum-Welch statistics and in the derivation of the posterior expectation of the i-vector. We conduct experiments on the NIST-SRE corpus mixed with real domestic noise and reverberation from the CHiME-2 corpus and preprocessed by multichannel speech enhancement. The proposed method improves the equal error rate (EER) by 4% relative compared to a conventional i-vector based speaker verification baseline. This is to be compared with previous methods which degrade performance.

show abstract

“…In [6][7] [8], the variance of i-vectors for short utterances are modeled and used for i-vector normalization. [9] and [10] proposed to utilize duration information in PLDA model. [11] uses phonetic information to reconstruct reliable i-vectors.…”

Section: Introductionmentioning

confidence: 99%

I-vector Transformation Using Conditional Generative Adversarial Networks for Short Utterance Speaker Verification

2018

View full text Add to dashboard Cite

I-vector based text-independent speaker verification (SV) systems often have poor performance with short utterances, as the biased phonetic distribution in a short utterance makes the extracted i-vector unreliable. This paper proposes an i-vector compensation method using a generative adversarial network (GAN), where its generator network is trained to generate a compensated i-vector from a short-utterance i-vector and its discriminator network is trained to determine whether an i-vector is generated by the generator or the one extracted from a long utterance. Additionally, we assign two other learning tasks to the GAN to stabilize its training and to make the generated ivector more speaker-specific. Speaker verification experiments on the NIST SRE 2008 "10sec-10sec" condition show that our method reduced the equal error rate by 11.3% from the conventional i-vector and PLDA system.

show abstract

Fast scoring for PLDA with uncertainty propagation via i-vector grouping

Cited by 20 publications

References 16 publications

Speaker Recognition With Random Digit Strings Using Uncertainty Normalized HMM-Based i-Vectors

Speaker Recognition With Random Digit Strings Using Uncertainty Normalized HMM-Based i-Vectors

An Improved Uncertainty Propagation Method for Robust I-vector Based Speaker Recognition

I-vector Transformation Using Conditional Generative Adversarial Networks for Short Utterance Speaker Verification

Contact Info

Product

Resources

About