Myanmar Continuous Speech Recognition System Using Convolutional Neural Network

Chit, Yin Win; Hlaing, Win Ei; Khaing, Myo

doi:10.5815/ijigsp.2021.02.04

Cited by 3 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It specifies the location of another spectrum's centroid. It seems to have a powerful sensory link that creates the impression of volume increase [2]. It's being used to connect the midpoint to some other metric just on spectral region, as well as the variance behind them is essentially almost the same as the actual variance seen between overall average means and standard deviations values.…”

Section: Spectral Centroidmentioning

confidence: 99%

“…Here the 'ith' normalised DFT component inside the 'ith' block is determined as the absolute differences between certain standardized dimensions also with wavelengths upon those two (2) subsequent quick frames. Over the next algorithm, the spectrum energy would be performed again: 𝐹𝑙 (𝑖,𝑖−1) = ∑ (𝐸𝑁 𝑖 (𝑘) − 𝐸𝑁 𝑖−1 (𝑘) ) 2 𝑊𝑓 𝑙 𝑘=1 (6) The graphs show the average value of spectrum energy evolution of sections divided into two (2) categories: voice or musical. It can be seen that overall spectrum energy increments with voice frequency.…”

Section: Spectral Fluxmentioning

confidence: 99%

See 1 more Smart Citation

Enhanced Deep Hierarchal GRU & BILSTM using Data Augmentation and Spatial Features for Tamil Emotional Speech Recognition

Fernandes¹,

Mannepalli²

2022

IJMECS

View full text Add to dashboard Cite

The Recurrent Neural Network (RNN) is well suited for emotional speech recognition because its uses constantly time shifting property. Even though RNN gives better results GRU, LSTM and BILSTM solves the gradient problem and overfitting problem joins the path to reduces the efficiency. Hence in this paper five deep learning architecture is designed in order to overcome the major issues using data augmentation and spatial feature. Five different architectures like: Enhanced Deep Hierarchal LSTM & GRU (EDHLG), EDHBG, EDHGL, EDHGB & EDHGG are developed with dropout layers. The raw data learned from LSTM will be given as the input to GRU layer for deepest learning. Thus, the gradient problem is reduced, and accuracy of each emotion was increased. Also, to enhance the accuracy level spatial features were concatenated with MFCC. Thus, in all models, the experimental evaluation with the Tamil emotional dataset yielded the best results. EDHLG has a 93.12% accuracy, EDHGL has a 92.56 percent accuracy, EDHBG has a 95.42 percent accuracy, EDHGB has a 96 percent accuracy, and EDHGG has a 94 percent accuracy. Furthermore, the average accuracy rate of a single individual LSTM layer is 74%, while BILSTM is 77%. EDHGB outperforms almost all other systems, by an optimal system of 94.27 percent and then a maximum overall accuracy of 95.99 percent. For the Tamil emotion data, emotional states such as happy, fearful, angry, sad, and neutral have a 100% prediction accuracy, while disgust has a 94 percent efficiency rate and boredom has an 82 percent accuracy rate. Also, the training time and evaluation time utilized by EDHGB is 4.43 mins and 0.42 mins which is less when compared with other models. Hence by changing the LSTM, BILSTM and GRU layers large analysis of experiment on Tamil dataset is done and EDHGB is superior to other models, and when compared with basic models LSTM and BILSTM around 26% more efficiency is gained.

show abstract

Section: Spectral Centroidmentioning

confidence: 99%

Section: Spectral Fluxmentioning

confidence: 99%

Enhanced Deep Hierarchal GRU & BILSTM using Data Augmentation and Spatial Features for Tamil Emotional Speech Recognition

Fernandes¹,

Mannepalli²

2022

IJMECS

View full text Add to dashboard Cite

show abstract

Syllable-Based Myanmar Speech-to-Text ASR using Deep Learning and CTC

Myo,

Thet,

Htun

et al. 2024

2024 Conference of Young Researchers in Electrical and Electronic Engineering (ElCon)

View full text Add to dashboard Cite

Multiple Musical Instrument Signal Recognition Based on Convolutional Neural Network

Lei

2022

Scientific Programming

View full text Add to dashboard Cite

To improve the accuracy of multi-instrument recognition, based on the basic principles and structure of CNN, a multipitch instrument recognition method based on the convolutional neural network (CNN) is proposed. First of all, the pitch feature detection technology and constant Q transform (CQT) are adopted to extract the signal characteristics of multiple instruments, which are used as the input of the CNN network. Moreover, in order to improve the accuracy of multi-instrument signal recognition, the benchmark recognition model and two-level recognition model are constructed. Finally, the above models are verified by experiments. The results show that the two-level classification model established in this article can accurately identify and classify various musical instruments, and the recognition accuracy is improved most obviously in xylophone. Compared with the benchmark model, the constructed two-level recognition has the highest accuracy and precision, which shows that this model has superior performance and can improve the accuracy of multi-instrument recognition.

show abstract

Myanmar Continuous Speech Recognition System Using Convolutional Neural Network

Cited by 3 publications

References 3 publications

Enhanced Deep Hierarchal GRU & BILSTM using Data Augmentation and Spatial Features for Tamil Emotional Speech Recognition

Enhanced Deep Hierarchal GRU & BILSTM using Data Augmentation and Spatial Features for Tamil Emotional Speech Recognition

Syllable-Based Myanmar Speech-to-Text ASR using Deep Learning and CTC

Multiple Musical Instrument Signal Recognition Based on Convolutional Neural Network

Contact Info

Product

Resources

About