Entropy coding of compressed feature parameters for distributed speech recognition

Lee, Young Han; Kim, Hong Kook

doi:10.1016/j.specom.2010.01.002

Cited by 4 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Speech intelligibility in noisy environments, another relevant theme, can be predicted with CSE evaluation, as documented in [12] and [74] . Entropy has also played an important role in speech recognition, as shown by the authors of papers [48,54,78] . Particular types of speech signals may be accurately characterized with the use of entropy, as the authors of paper [85] demonstrate.…”

Section: A Review On Entropy and Its Applicationsmentioning

confidence: 99%

A tutorial review on entropy-based handcrafted feature extraction for information fusion

Guido

2018

Information Fusion

View full text Add to dashboard Cite

Entropy (H) is the main subject of this article, concisely written to serve as a tutorial introducing two feature extraction (FE) methods for usage in digital signal processing (DSP) and pattern recognition (PR). The theory, carefully exposed, is supplemented with numerical cases, augmented with C/C ++ sourcecodes and enriched with example applications on restricted-vocabulary speech recognition and image synthesis. Complementarily and as innovatively shown, the ordinary calculation of H corresponds to the outcome of a partially pre-tuned deep neural network architecture which fuses important information, bringing a cutting-edge point-of-view for both DSP and PR communities.

show abstract

Section: A Review On Entropy and Its Applicationsmentioning

confidence: 99%

A tutorial review on entropy-based handcrafted feature extraction for information fusion

Guido

2018

Information Fusion

View full text Add to dashboard Cite

show abstract

“…The combination of entropy and MFCC has been used in speech recognition to improve its performance and robustness in the presence of additive noise [19], [20], [21]. The present study explores the entropy of the mel frequency cepstrum spectrum as feature for the blind identification of source mobile devices.…”

Section: A Feature Extractionmentioning

confidence: 99%

Blind identification of source mobile devices using VoIP calls

Jahanirad

Wahab

Anuar

et al. 2014

2014 Ieee Region 10 Symposium

View full text Add to dashboard Cite

Sources such as speakers and environments from different communication devices produce signal variations that result in interference generated by different communication devices. Despite these convolutions, signal variations produced by different mobile devices leave intrinsic fingerprints on recorded calls, thus allowing the tracking of the models and brands of engaged mobile devices. This study aims to investigate the use of recorded Voice over Internet Protocol calls in the blind identification of source mobile devices. The proposed scheme employs a combination of entropy and mel-frequency cepstrum coefficients to extract the intrinsic features of mobile devices and analyzes these features with a multi-class support vector machine classifier. The experimental results lead to an accurate identification of 10 source mobile devices with an average accuracy of 99.72%.

show abstract

“…Main section source is sorted by probability. Auxiliary section source is encoded according to shifting coding sequence and adding the "up-shift word or down-shift word" [4][5][6][7][8].…”

Section: A Shift Huffman Codingmentioning

confidence: 99%

Intelligent Clothing Embedded GPS Data Processing Based on Shifting Huffman Coding

Ren

Ding

2012

AMM

View full text Add to dashboard Cite

According to the characteristic of GPS system fo intelligent garment, this paper presents a strategy of GPS data processing by removing redundant information and shifting the combination codes. Its compressed result is analyzed by comparing with direct data compression and Huffman coding. The above-mentioned strategy takes into account both the speed and the effect of the compression, and has a good performance in the compression rate. The non-destructive GPS data processing method has a positive and practical significance in the intelligent garment for efficient monitoring.

show abstract

Entropy coding of compressed feature parameters for distributed speech recognition

Cited by 4 publications

References 14 publications

A tutorial review on entropy-based handcrafted feature extraction for information fusion

A tutorial review on entropy-based handcrafted feature extraction for information fusion

Blind identification of source mobile devices using VoIP calls

Intelligent Clothing Embedded GPS Data Processing Based on Shifting Huffman Coding

Contact Info

Product

Resources

About