Short-time Gaussianization for robust speaker verification

Xiang, Bing; Chaudhari, Upendra V.; Navrátil, Jǐŕı; Ramaswamy, Ganesh N.; Gopinath, R.

doi:10.1109/icassp.2002.5743809

Cited by 91 publications

(53 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For telephone speech, the VAD labels are produced by a Hungarian phoneme recognizer [33,34] and for microphone speech, VAD labels are generated using a GMM-based VAD by training one GMM for nonspeech and another one for speech [35]. Final features are obtained after appending the delta and double delta features and normalizing the features using a short-time Gaussianization (STG) method [24,40].…”

Section: Multi-taper Mfcc and Plp Feature Extractionmentioning

confidence: 99%

See 1 more Smart Citation

Multitaper MFCC and PLP features for speaker verification using i-vectors

Alam

Kinnunen

Kenny

et al. 2013

Speech Communication

View full text Add to dashboard Cite

In this paper we study the performance of the low-variance multi-taper Mel-frequency cepstral coefficient (MFCC) and perceptual linear prediction (PLP) features in a state-ofthe-art i-vector speaker verification system. The MFCC and PLP features are usually computed from a Hamming-windowed periodogram spectrum estimate. Such a singletapered spectrum estimate has large variance, which can be reduced by averaging spectral estimates obtained using a set of different tapers, leading to a so-called multitaper spectral estimate. The multi-taper spectrum estimation method has proven to be powerful especially when the spectrum of interest has a large dynamic range or varies rapidly. Multi-taper MFCC features were also recently studied in speaker verification with promising preliminary results. In this study our primary goal is to validate those findings using an up-to-date i-vector classifier on the latest NIST 2010 SRE data. In addition, we also propose to compute robust perceptual linear prediction (PLP) features using multitapers. Furthermore, we provide a detailed comparison between different taper weight selections in the Thomson multi-taper method in the context of speaker verification. Speaker verification results on the telephone (det5) and microphone speech (det1, det2, det3 and det4) of the latest NIST 2010 SRE corpus indicate that the multitaper methods outperform the conventional periodogram technique. Instead of simply averaging (using uniform weights) the individual spectral estimates in forming the multitaper estimate, weighted averaging (using non-uniform weights) improves performance.Compared to the MFCC and PLP baseline systems, the sine-weighted cepstrum estimator 2 (SWCE) based multitaper method provides average relative reductions of 12.3% and 7.5% in equal error rate, respectively. For the multi-peak multi-taper method, the corresponding reductions are 12.6% and 11.6%, respectively. Finally, the Thomson multitaper method provides error reductions of 9.5% and 5.0% in EER for MFCC and PLP features, respectively. We conclude that both the MFCC and PLP features computed via multitapers provide systematic improvements in recognition accuracy.

show abstract

Section: Multi-taper Mfcc and Plp Feature Extractionmentioning

confidence: 99%

“…Nonspeech frames are then removed using pre-computed VAD labels using algorithms mentioned in section 3. For feature normalization, we apply the short-time Gaussianization (STG) technique [24,40] over a 300-frame window.…”

Section: Feature Extractionmentioning

confidence: 99%

Multitaper MFCC and PLP features for speaker verification using i-vectors

Alam

Kinnunen

Kenny

et al. 2013

Speech Communication

View full text Add to dashboard Cite

show abstract

“…For the acoustic GMM-UBM system [1], we applied several channel compensation techniques, including feature warping [40], Z-norm [41], short-time Gaussianization (STG) [42] and fast blind stochastic feature transformation (fBSFT) [43]. Acoustic scores S GMM-UBM were computed based on the loglikelihood ratio:…”

Section: Scoring Methodsmentioning

confidence: 99%

A new adaptation approach to high-level speaker-model creation in speaker verification

Zhang

Mak

2009

Speech Communication

View full text Add to dashboard Cite

Research has shown that speaker verification based on high-level speaker features requires long enrollment utterances to guarantee low error rate during verification. However, in practical speaker verification, it is common to model speakers based on a limited amount of enrollment data, which will make the speaker models unreliable. This paper proposes four new adaptation methods for creating high-level speaker models to alleviate this undesirable effect. Unlike conventional methods in which only the phoneme-dependent background model is adapted, the proposed adaptation methods also adapts the phoneme-independent speaker model to fully utilize all the information available in the training data. A proportional factor, which is derived from the ratio between the phoneme-dependent background model and the phoneme-independent background model, is used to adjust the phonemeindependent speaker models during adaptation. The proposed method was evaluated under the NIST 2000 and NIST 2002 SRE frameworks. Experimental results show that the proposed adaptation method can alleviate the data-sparseness problem effectively and achieves a better performance when compared with traditional MAP adaptation.

show abstract

“…Feature warping has been shown to be robust to different channel and noise effects. In short-time Gaussianization [10], a linear transformation is applied to the distorted feature before mapping them to a normal distribution. The transformation aims to decorrelate the feature vectors, making them more amendable to diagonal covariance GMMs.…”

Section: Blind Compensationmentioning

confidence: 99%

Probabilistic Feature Transformation for Channel Robust Speaker Verification

Mak

Yiu

2006

2006 16th IEEE Signal Processing Society Workshop on Machine Learning for Signal Processing

View full text Add to dashboard Cite

Feature transformation plays an important role in robust speaker verification over telephone networks. This paper compares several feature transformation techniques and evaluates their verification performance and computation time under the 2000 NIST speaker recognition evaluation protocol. Techniques compared include feature mapping (FM), stochastic feature transformation (SFT), and blind stochastic feature transformation (BSFT). The paper proposes a probabilistic feature mapping (PFM) in which the mapped features depend not only on the top-1 decoded Gaussian but also on the posterior probabilities of other Gaussians in the root model. The paper also proposes speeding up the computation of PFM and BSFT parameters by considering the top few Gaussians only. Results show that PFM performs slightly better than FM and that the fast approach can reduce computation time substantially. Among the approaches investigated, the fast BSFT is found to have the highest potential for robust speaker verification over telephone networks because it can achieve good performance without any a priori knowledge of the communication channel. It was also found that fusion of the scores derived from systems using BSFT and PFM can reduce the error rate further.

show abstract

Short-time Gaussianization for robust speaker verification

Cited by 91 publications

References 5 publications

Multitaper MFCC and PLP features for speaker verification using i-vectors

Multitaper MFCC and PLP features for speaker verification using i-vectors

A new adaptation approach to high-level speaker-model creation in speaker verification

Probabilistic Feature Transformation for Channel Robust Speaker Verification

Contact Info

Product

Resources

About