An automatic speech recognition system for helping visually impaired children to learn Braille

Ramlrez, Melissa; Sotaquirá, Miguel; Cruz, Alberto De La; Esther, María; Avellaneda, Gustavo; Ochoa, Ana Cecilia

doi:10.1109/stsiva.2016.7743335

Cited by 9 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Mel-Frequency Cepstral (MFC) is a well-known method for extracting the speech signal features. A smart combination of the MFC and the Dynamic Time Warping (DTW) techniques can provide effective solutions especially in the case of isolated speech words recognition [23,26,32]. The devised system deals with the isolated speech word.…”

Section: Methodsmentioning

confidence: 99%

“…It has diverse applications like smart cities, secure access, rehabilitation centres, criminals investigation analysis, banks, hands free assistance, commanding a robot, data security, virtual reality, Multimedia searches, auto-attendants, travel Information and reservation, translators, natural language understanding, etc. [15,16,[19][20][21][22][23][24]. These systems are founded on the machine based speech comprehension and recognition.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Speech Recognition and a Cymatics Based Configurable Speech Perception

Qaisar¹

2018

Preprint

View full text Add to dashboard Cite

This paper propose an original approach of achieving a Cymatics based visual perception of isolated speech commands. The idea is to smartly combine the effective speech processing and analysis methods with the phenomena of Cymatics. In this context, an effective approach for automatic isolated speech based message recognition is proposed. The incoming speech segment is enhanced by applying the appropriate pre-emphasis filtering, noise thresholding and zero alignment operations. The Mel-Frequency Cepstral coefficients (MFCCs), Delta coefficients and Delta-Delta coefficients are extracted from the enhanced speech segment. Later on, the Dynamic Time Warping (DTW) technique is employed to compare these extracted features with the reference templates. The comparison outcomes are used to make the classification decision. The classification decision is transformed into a methodical excitation. Finally, this excitation is converted into the systematic visual perceptions via the phenomenon of Cymatics. The system functionality is tested with an experimental setup and results are presented. The approach is novel and can be employed in various applications like visual art, encryption, education, archeology, architecture, integration of impaired people, etc.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Speech Recognition and a Cymatics Based Configurable Speech Perception

Qaisar¹

2018

Preprint

View full text Add to dashboard Cite

show abstract

“…After testing the algorithm the device showed 89% positive approximation. This device inputs data using a microphone and gives output in a text format [9].…”

Section: Literature Reviewmentioning

confidence: 99%

Deep Learning based Bangla Voice to Braille Character Conversion System

Hussain

Rifat

Iqbal

et al. 2022

2022 IEEE 13th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)

View full text Add to dashboard Cite

From the very beginning of the 20th century, there has been a significant development in the education system using modern technology. However, this rapid development has very little scope to facilitate the education system for the people without sight. Though braille is a method for sight disabled people it has not been incorporated that much with the modern education system. On the other hand, many papers and works have been done on it but a maximum of these is about the conversion of a text character to a braille pattern with considerable accuracy so far no work has been done that can work with voice to convert a character into braille pattern for Bangla language. This paper introduces a development that will help the visually impaired people to start their very basic education with a technology that is capable of recognizing a Bangla character uttered by a person and can convert that character into braille pattern so that using a finger touch one can recognize the corresponding braille for that character. This voice recognition will be done using the Visual Geometry Group (VGG-16) model of Convolutional Neural Network (CNN) and Arduino Uno, LCD 16x4 display will be used to generate the braille pattern for the recognized character. The model is trained with 50 epochs and we achieved 98% of train accuracy and after evaluating test data we gained 92.42% test accuracy.

show abstract

“…It consists mainly of multiply-accumulate logic, followed by logarithm base-2 log 2 block. Additional multiplexers and subtractors are implemented to compute the constants in (8). The log block is explained in the next subsection.…”

Section: First Feature Blockmentioning

confidence: 99%

“…For example, in medical applications, speech recognition systems are used in enhancing learning performance, attention, and meditation [2]; speech therapy [3]; communicating with elderly [4]; and patient assessment documentation [5]. In education, speech recognition systems assist non‐native English‐speakers [6], provide deaf‐hearing interactions at school and work [7], and help visually impaired children to learn Braille [8]. At home, speech recognition systems control home appliances, personalised educational toys and voice‐based multi‐player gaming [9].…”

Section: Introductionmentioning

confidence: 99%

Implementation of speech feature extraction for low‐resource devices

Abed

Mohd

Shayeji

2019

IET Circuits, Devices & Systems

View full text Add to dashboard Cite

Feature extraction is an important function in the speech recognition system. Employing a speech recognition system in low-resource devices (LRDs) have increased significantly in recent years. Implementing feature extraction, which involves complex computations, in LRD is very challenging because LRD has limited energy, storage, and processing power. The optimum design must carefully balance performance metrics, including speed, area, and energy. The objective of this research is to implement and model speech feature extraction design in a field-programmable gate array (FPGA) platform, and to identify the optimum implementation for low-resource devices (LRDs). The novelty of this research is optimising feature extraction implementations using design options such as word size; and developing accurate performance models to enhance future designs. The authors study extensively examines the effect of fixed-point n-bit word size on the design of Mel frequency cepstral coefficients feature extraction in the FPGA implementation. The results show that the performance metrics (area, power, and energy) increase at a slower pace compared with n because the dependency of some blocks (e.g. logarithm) on n is non-linear. For example, increasing n by 50% increases the resource utilisation by 38%, power by 41% and energy by 41%. Models for resources, power, and energy are developed with accuracies of 5.1, 4.5, and 4.3%, respectively. Furthermore, n has a weak impact on timing results and therefore speed is almost similar across implementations. Each bit (in n) costs 690 logical elements in the area, 2.35 mW in power and 0.55μJ in energy. For LRD, the 32-bit design demonstrates the most optimum design, followed by 48-bit and 24-bit designs.

show abstract

An automatic speech recognition system for helping visually impaired children to learn Braille

Cited by 9 publications

References 5 publications

Speech Recognition and a Cymatics Based Configurable Speech Perception

Speech Recognition and a Cymatics Based Configurable Speech Perception

Deep Learning based Bangla Voice to Braille Character Conversion System

Implementation of speech feature extraction for low‐resource devices

Contact Info

Product

Resources

About