Improved cepstral mean and variance normalization using Bayesian framework

Prasad, Nitin; Umesh, S.

doi:10.1109/asru.2013.6707722

Cited by 33 publications

(16 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cepstral Mean and Variance Normalization (CMVN) is a simple and effective feature domain technique to deal with mismatch conditions [1]. Speaker adaptation techniques in model domain have been reported in [2], [3] to compensate speaker mismatch.…”

Section: Introductionmentioning

confidence: 99%

Psychoacoustic model compensation for robust continuous speech recognition in additive noise

Das¹,

Panda²

2015

2015 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)

View full text Add to dashboard Cite

This paper addresses the problem of speech recognition in the presence of additive noise. It focuses on Psychoacoustic Model Compensation (Psy-Comp) scheme, which has been shown to be a powerful technique for noise robustness. It has further implemented model domain mean and variance normalization along with Psy-Comp to alleviate channel noise for robust continuous speech recognition in noisy conditions. The proposed algorithms are validated through experiments on noise corrupted TIMIT speech recognition database. We show that the PsyComp scheme along with model domain mean and variance normalization provide 9.5% performance gain compared to the Vector Taylor Series (VTS) scheme. Moreover, the computational cost of the proposed method is significantly less than the VTS scheme.

show abstract

Section: Introductionmentioning

confidence: 99%

Psychoacoustic model compensation for robust continuous speech recognition in additive noise

Das¹,

Panda²

2015

2015 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)

View full text Add to dashboard Cite

show abstract

“…To this aim, we propose archetypal analysis (AA) [7] based sparse convex sequence kernel (SCSK) for the BAD task. Further, to mitigate channel and environment variations, the extracted short-time features are preprocessed with cepstral mean and variance normalization (CMVN) [10], and short-time feature warping (Gaussianization) techniques [11], which are widely used in context of automatic speaker recognition.…”

Section: Introductionmentioning

confidence: 99%

Archetypal analysis based sparse convex sequence kernel for bird activity detection

Abrol

Sharma

Thakur

et al. 2017

2017 25th European Signal Processing Conference (EUSIPCO)

View full text Add to dashboard Cite

Abstract-This paper proposes a novel method based on the archetypal analysis (AA) for bird activity detection (BAD) task. The proposed method extracts a convex representation (frame-wise) by projecting a given audio signal on to a learned dictionary. The AA based dictionary is trained only on bird class signals, which makes the method robust to background noise. Further, it is shown that due to the inherent sparsity property of convex representations, non-bird class signals will have a denser representation as compared to the bird counterpart, which helps in effective discrimination. In order to detect presence/absence of bird vocalization, a fixed length representation is obtained by averaging the obtained frame wise representations of an audio signal. Classification of these fixed length representations is performed using support vector machines (SVM) with a dynamic kernel. In this work, we propose a variant of probabilistic sequence kernel called sparse convex sequence kernel (SCSK) for the BAD task. Experimental results show that the proposed method can efficiently discriminate bird from non-bird class signals.

show abstract

“…The main aims of using normalization are to reduce the effects of noise, channel, and handset transducers and to alleviate linear and non-linear channel effects. In this study, feature warping (FW) and cepstral mean and variance normalization (CMVN) over a sliding window are used [39,40] to reduce the noise and handset effects and mitigate linear channel effects; this gives improvements and robustness to SIA [6]. The features and feature normalization are as employed in [29].…”

Section: Feature Extraction and Compensationmentioning

confidence: 99%

Evaluation of a speaker identification system with and without fusion using three databases in the presence of noise and handset effects

Al-Kaltakchi

Woo

Dlay

et al. 2017

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

In this study, a speaker identification system is considered consisting of a feature extraction stage which utilizes both power normalized cepstral coefficients (PNCCs) and Mel frequency cepstral coefficients (MFCC). Normalization is applied by employing cepstral mean and variance normalization (CMVN) and feature warping (FW), together with acoustic modeling using a Gaussian mixture model-universal background model (GMM-UBM). The main contributions are comprehensive evaluations of the effect of both additive white Gaussian noise (AWGN) and non-stationary noise (NSN) (with and without a G.712 type handset) upon identification performance. In particular, three NSN types with varying signal to noise ratios (SNRs) were tested corresponding to street traffic, a bus interior, and a crowded talking environment. The performance evaluation also considered the effect of late fusion techniques based on score fusion, namely, mean, maximum, and linear weighted sum fusion. The databases employed were TIMIT, SITW, and NIST 2008; and 120 speakers were selected from each database to yield 3600 speech utterances. As recommendations from the study, mean fusion is found to yield overall best performance in terms of speaker identification accuracy (SIA) with noisy speech, whereas linear weighted sum fusion is overall best for original database recordings.

show abstract

Improved cepstral mean and variance normalization using Bayesian framework

Cited by 33 publications

References 8 publications

Psychoacoustic model compensation for robust continuous speech recognition in additive noise

Psychoacoustic model compensation for robust continuous speech recognition in additive noise

Archetypal analysis based sparse convex sequence kernel for bird activity detection

Evaluation of a speaker identification system with and without fusion using three databases in the presence of noise and handset effects

Contact Info

Product

Resources

About