Implementation of Efficient Speech Recognition System on Mobile Device for Hindi and English Language

Dharmale, Gulbakshee; Patil, Dipti D.; Thakare, V. M.

doi:10.14569/ijacsa.2019.0100212

Cited by 6 publications

(2 citation statements)

References 4 publications

(4 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The classifier is trained and a state probability model is developed, this model consists of chains of frequently occurring words connected via the probability of each of the words occurring together. The training corpus consists of a large set of words taken from online sources like UCI textual dataset repository, twitter and other social media datasets [14].The word linkages are then stored in the database via forward indexing, and this index is then further used for comparison. Whenever a new speech sample is taken, it is first converted into text using existing speech to text technique; the resulting text is then given to the HMM-map.…”

Section: Phonetic System For Speech Recognitionmentioning

confidence: 99%

Evaluation of Phonetic System for Speech Recognition on Smartphone

Dharmale¹,

Patil²

2019

IJITEE

View full text Add to dashboard Cite

This paper presents detailed study and performance evaluation of phonetic system by comparing it with various classification techniques of automatic speech recognition such as Neural Network, Hidden Markov Model, Support Vector Machine and Gaussian Mixture Model. In the phonetic system, recognized speech is processed by using language processing i.e. matching phonemes and hence generates more correct output text. The accuracy of speech recognition of ASR classifier and phonetic system is evaluated on day to day human to machine communications, using high-quality recording equipment, while the results for enhancement of existing systems is done on everyday android phones, and evaluated for normal conversations in Hindi and English language. Classifier is used to classify the fragmented phonemes or words after the fragmentation of the speech signal. Different classification techniques are implemented and comparing accuracy of speech recognition of different classifier. It is seen that GMM is better at the classification of signal data, outcomes of performance evaluation shows that GMM outperforms the other three classifiers in terms of accuracy by more than 20%. This result is compared with implemented phonetic system which shows that ASR accuracy, using phonetic system is better than GMM. We observed 6% improvement in ASR accuracy with phonetic system.

show abstract

Section: Phonetic System For Speech Recognitionmentioning

confidence: 99%

Evaluation of Phonetic System for Speech Recognition on Smartphone

Dharmale¹,

Patil²

2019

IJITEE

View full text Add to dashboard Cite

show abstract

“…Speech recognition is utilized to change over talked shape into content to help people needs [3]. The speech recognition system is widely used for smart applications, e.g., intelligent wheelchair, Google assistant, Alexa, Cortana, Siri, and home assistant [4], [5]. Each smart application-based speech recognition system has different requirements for processing the human voice.…”

Section: Introductionmentioning

confidence: 99%

Performance Comparison between Lab-VIEW and MATLAB on Feature Matching-based Speech Recognition System

Widasari¹,

Prasetio²,

Ratnawati³

2022

IJACSA

View full text Add to dashboard Cite

Speech recognition systems are widely used for smart applications. The smart application-based speech recognition system has different requirements for processing the human voice. The most common performance in the speech recognition system is essential to observe, since it is necessary to design smart application-based speech recognition systems for people's needs. Moreover, feature matching is the principal part of speech recognition systems since it plays a key role to authenticate, separate one human voice from another, and their different articulation. Therefore, this work proposes a performance comparison of speech recognition systems based on feature matching using Lab-VIEW and MATLAB. The feature extraction involves calculation of Mel Frequency Cepstral Coefficients (MFCC) for each frame. For the matching process, the system was tested 100 times for each five speeches by making changes in articulation with the same vocal cords. This matching process uses DTW (Dynamic Time Warping), and then the testing is based on the most common performance in the speech recognition system's comparison between Lab-VIEW and MATLAB such as accuracy rate, execution time, and CPU usage. Based on experimental results, the average accuracy rate of MATLAB is better than Lab-VIEW. The execution time testing indicates that Lab-VIEW has a shorter execution time than MATLAB. On the other hand, Lab-VIEW and MATLAB have almost the same CPU usage. This result indicates that the performance comparison is able to be used according to the requirements of smart application-based speech recognition systems.

show abstract

A proof-of-concept study for automatic speech recognition to transcribe AAC speakers’ speech from high-technology AAC systems

Chen,

Saeli,

2023

Assistive Technology

View full text Add to dashboard Cite

Implementation of Efficient Speech Recognition System on Mobile Device for Hindi and English Language

Cited by 6 publications

References 4 publications

Evaluation of Phonetic System for Speech Recognition on Smartphone

Evaluation of Phonetic System for Speech Recognition on Smartphone

Performance Comparison between Lab-VIEW and MATLAB on Feature Matching-based Speech Recognition System

A proof-of-concept study for automatic speech recognition to transcribe AAC speakers’ speech from high-technology AAC systems

Contact Info

Product

Resources

About