Lip reading using fuzzy logic network with memory

Badura, Stefan; Klimo, Martin; Škvarek, Ondrej

doi:10.1109/icaict.2012.6398471

Cited by 5 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For future work, more features are need to be extracted in other sense parts. Anacquaint with fuzzy logic network that overcomes the disadvantages of neural network classifiers are introduced by in [10]. In general, the steps involved in lip reading are feature extraction from face area and distinguishing the speech.…”

Section: Related Workmentioning

confidence: 99%

A Systematic Study and Empirical Analysis of Lip Reading Models using Traditional and Deep Learning Algorithms

Sangeetha¹,

Malathi²

2022

JOAASR

View full text Add to dashboard Cite

Despite the fact that there are many applications for analyzing and recreating the audio through existinglip movement recognition, the researchers have shown the interest in developing the automatic lip-readingsystems to achieve the increased performance. Modelling of the framework has been playing a major role inadvance yield of sequential framework. In recent years there have been lot of interest in Deep Neural Networks(DNN) and break through results in various domains including Image Classification, Speech Recognition andNatural Language Processing. To represents complex functions DNNs are used and also they play a vital rolein Automatic Lip Reading (ALR) systems. This paper mainly focuses on the traditional pixel, shape and mixedfeature extractions and their improved technologies for lip reading recognitions. It highlights the mostimportant techniques and progression from end-to-end deep learning architectures that were evolved duringthe past decade. The investigation points out the voice-visual databases that are used for analyzing and trainthe system with the most common words and the count of speakers and the size, length of the language andtime duration. On the flip side, ALR systems developed were compared with their old-style systems. Thestatistical analysis is performed to recognize the characters or numerals and words or sentences in English andcompared their performances.

show abstract

Section: Related Workmentioning

confidence: 99%

A Systematic Study and Empirical Analysis of Lip Reading Models using Traditional and Deep Learning Algorithms

Sangeetha¹,

Malathi²

2022

JOAASR

View full text Add to dashboard Cite

show abstract

“…Both of these functions can be implemented using bistable complementary resistive switches [5], [6] as indicated in circuits diagrams in Figure 1. There are other approaches that use the same processing elements [7], [8], [9], [10], [11], [12] as well as a vast body of research on more general fuzzy logic systems. The difference in our work is that we strived to achieve two invariance properties of the resulting network.…”

Section: Introductionmentioning

confidence: 99%

Phoneme discrimination using a pair of neurons built from CRS fuzzy logic gates

Šuch¹,

Klimo²,

Škvarek³

2015

AIP Conference Proceedings

Self Cite

View full text Add to dashboard Cite

We consider the ability of a very simple feed-forward neural network to discriminate phonemes based on just relative power spectrum. The network consists of two neurons with symmetric nonlinear response over a spectral range. The neurons are built from complementary resistive switches. The output of the neurons is subsequently fed to a comparator. We show that often this is enough to achieve complete separation of data. The networks considered are directly amenable to hardware (neuromorphic) designs. Other advantages include interpretability, guarantees of performance on unseen data and low Kolmogorov complexity.

show abstract

“…First steps were taken in works [11], [12], [13], [14], [15] where authors find pattern recognition circuits using fuzzy logic operators. Their application domain is speech recognition.…”

Section: Introductionmentioning

confidence: 99%