The voice recognition of non-native tongue English learners is an important challenge in the field of speech recognition. Existing technology still has obvious defects when dealing with non-native tongue pronunciation...
详细信息
The voice recognition of non-native tongue English learners is an important challenge in the field of speech recognition. Existing technology still has obvious defects when dealing with non-native tongue pronunciation. This study combined BERT (Bidirectional Encoder Representations from Transformers) and CNN-HMM models and introduced an attention mechanism to improve the accuracy of voice recognition of non-native tongue English learners. It used the pre-trained BERT model to extract the context of the voice signal and used the CNN (convolutionalneuralnetwork) for local feature extraction, and used the hiddenmarkovmodel (HMM) to make a sequence model building model to capture ability of key features. The experimental results show that the accuracy rate of voice recognition of the BERT-CNN-HMM model in this article reaches 88.9% under normal speed, which is significantly better than 78.5% of the traditional HMM model. Under different noise levels, the accuracy of the article's model in low noise, medium noise, and high noise environments is 86.9%, 80.5%, and 72.8%, respectively, which are higher than other comparative models. The accuracy of the models in this article remained above 83.8% when processing different accents, showing strong adaptation to strong adaptation and generality. It can be seen from the experimental results that the model of this article can significantly improve the accuracy of the voice recognition of non-native English learners and provide a new direction for further research in the field of voice recognition.
There is a growing interest in using Deep learning (DL) to analyse sensor data for monitoring heart-rate, aiming for earlier and accurate prediction of cardiovascular diseases (CvD). However, the resource-intensive na...
详细信息
ISBN:
(纸本)9798350350661;9798350350654
There is a growing interest in using Deep learning (DL) to analyse sensor data for monitoring heart-rate, aiming for earlier and accurate prediction of cardiovascular diseases (CvD). However, the resource-intensive nature of DL pose challenges, particularly on memory-limited devices like smartphones and other edge devices. To address this issue, we propose a novel approach that combines a convolutional neural network-hidden markov model (CNN-HMM). In this model, features from signals on smartphones or other edge devices are extracted using a CNN block, while classification is performed using an HMM. This CNN-HMM model offers advantages in processing non-stationary data and effectively extracting heart rate information. Additionally, we aim to address the challenge of Deep neuralnetwork (DNN) inference on resource-constrained edge devices by systematically comparing different light-weight models on several commercial hardware platforms (Raspberry Pi 4, high-performance computing (HPC) platforms) across popular frameworks, highlighting their performance and limitations. The proposed approach has achieved an accuracy of 96.39%, a precision of 96.27%, a recall of 97.20%, and an F1-score of 96.73% on NVIDIA Tesla T4 GPU (Graphics Processing Unit). Additionally, our model has demonstrated enhanced throughput, outperforming fine-tuned MobileNetV2, NASNet-Mobile, and MobileNetV3Small models by 77.62%, 138.65%, and 39.92% respectively on the Raspberry Pi 4 hardware platform.
暂无评论