Digit-Number Speech-Recognition using Spectrogram-Based Convolutional Neural Network

Amadeus, Clarence; Sutisna, Nana; Adiono, Trio

doi:10.1109/isesd56103.2022.9980803

Cited by 3 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed SpectroNet that we propose in this paper is based on the works done in [50]. The concept that we took is the hybrid CNN-LSTM idea, the choice of DenseNet as the CNN architecture, and the one-dimensional convolution concept used in the DenseNet.…”

Section: Real-time Abstractpotting Using Spectrogram-based Hybrid Cnn...mentioning

confidence: 99%

“…To further assess the performance of SpectroNet, we select several Deep Learning for Keyword Spotting models and train them with our dataset using as similar parameters as possible to the parameters stated in their respective papers. The models are AlexNet, which is the CNN model that we previously proposed in [52], SBNet, which is a CNN model that was created for environmental sound classification and is proposed in [53], DSCNN, a CNN model which uses depthwise separable convolution layer which is proposed in [54], and C1G2BiLSTM, a CNN-LSTM model proposed in [23]. They are all trained using the parameters stated in Table 9.…”

Section: A Deep Learning Model Designmentioning

confidence: 99%

See 1 more Smart Citation

Efficient Real-Time Smart Keyword Spotting Using Spectrogram-Based Hybrid CNN-LSTM for Edge System

Syafalni,

Amadeus,

Sutisna

et al. 2024

IEEE Access

Self Cite

View full text Add to dashboard Cite

Keyword Spotting (KWS) is the task of recognizing spoken command words from a database. With recent application human-machine interactions, KWS systems require real-time performance, where edge computing is a preferable option. To allow KWS systems to work on fast and real-time implementation, a low-complexity yet high-accurate AI model is mandatory. In this paper, we propose a comprehensive voice command recognition system design and its hardware implementation. The proposed AI model considered in this system is SpectroNet-based and an efficient hybrid CNN-LSTM architecture with low complexity. Jetson Xavier NX is an edge device because of its strong computational power as an embedded device. The implementation result shows the proposed method offers quite good in terms of accuracy, indicated by no accuracy drop between the model implemented in PC and Jetson Xavier. However, the inference time is quite high, which is 180 ms/step. To improve the speed of the system, the TensorRT library is used to further optimize the model. Optimization of the model is found effective, reducing 59.35% of the total operation performed in SpectroNet when FP32 precision is used, and 59.63% when FP16 precision is used. The model is also sped up by 45% if FP32 precision mode is used and 62% if FP16 precision mode is used. However, there is a slight accuracy drop of 2.68% if FP32 precision mode is used and 4.84% if FP16 precision mode is used. This slight drop in accuracy is considered negligible compared to the performance boost that TensorRT gives. The work is useful for intelligent control systems such as smart vehicles, smartphones, computers, and smart communications.

show abstract

Section: Real-time Abstractpotting Using Spectrogram-based Hybrid Cnn...mentioning

confidence: 99%

Section: A Deep Learning Model Designmentioning

confidence: 99%

Efficient Real-Time Smart Keyword Spotting Using Spectrogram-Based Hybrid CNN-LSTM for Edge System

Syafalni,

Amadeus,

Sutisna

et al. 2024

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

Multilingual and Mixed-lingual Digit Speech Recognition System for Indian Context

2023

2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT)

View full text Add to dashboard Cite

Unmasking the Truth: A Deep Learning Approach to Detecting Deepfake Audio Through MFCC Features

Altalahin,

AlZu'bi,

Alqudah

et al. 2023

2023 International Conference on Information Technology (ICIT)

View full text Add to dashboard Cite

Digit-Number Speech-Recognition using Spectrogram-Based Convolutional Neural Network

Cited by 3 publications

References 8 publications

Efficient Real-Time Smart Keyword Spotting Using Spectrogram-Based Hybrid CNN-LSTM for Edge System

Efficient Real-Time Smart Keyword Spotting Using Spectrogram-Based Hybrid CNN-LSTM for Edge System

Multilingual and Mixed-lingual Digit Speech Recognition System for Indian Context

Unmasking the Truth: A Deep Learning Approach to Detecting Deepfake Audio Through MFCC Features

Contact Info

Product

Resources

About