Xinghui Gao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xinghui Gao has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
Chengyun Zhang
3 shared publications- Chengyun Zhang
School of Electronics and Communication Engineering Guangzhou University Guangzhou People's Republic of China
2 shared publications Zezhou Hao
2 shared publications- Zezhou Hao
Research Institute of Tropical Forestry, Chinese Academy of Forestry, Guangzhou 510520, China
2 shared publications - Bowen Yu1 shared publication
Haisong Zhan
1 shared publication
Latest Publications
- Open Access
- 1 January 2027
- Published by KEAI Publishing in Avian Research
- Vol. 18 (1)
A prompt-enhanced CLAP framework for local few-shot bird sound classification
- 1 January 2027
- Published by KEAI Publishing in Avian Research
- Vol. 18 (1)
Open AccessA prompt-enhanced CLAP framework for local few-shot bird sound classification
- Open Access
- 17 February 2024
- Published by Elsevier in Ecological Indicators
- Vol. 159
Influence of recording devices and environmental noise on acoustic index scores: Implications for bird sound-based assessments
- 17 February 2024
- Published by Elsevier in Ecological Indicators
- Vol. 159
Open AccessInfluence of recording devices and environmental noise on acoustic index scores: Implications for bird sound-based assessments
- 1 September 2023
- Published by Elsevier in Applied Acoustics
- Vol. 212
One-step progressive representation transfer learning for bird sound classification
- 1 September 2023
- Published by Elsevier in Applied Acoustics
- Vol. 212
One-step progressive representation transfer learning for bird sound classification
- Open Access
Classification of Complicated Urban Forest Acoustic Scenes with Deep Learning Models
The use of passive acoustic monitoring (PAM) can compensate for the shortcomings of traditional survey methods on spatial and temporal scales and achieve all-weather and wide-scale assessment and prediction of environmental dynamics. Assessing the impact of human activities on biodiversity by analyzing the characteristics of acoustic scenes in the environment is a frontier hotspot in urban forestry. However, with the accumulation of monitoring data, the selection and parameter setting of the deep learning model greatly affect the content and efficiency of sound scene classification. This study compared and evaluated the performance of different deep learning models for acoustic scene classification based on the recorded sound data from Guangzhou urban forest. There are seven categories of acoustic scenes for classification: human sound, insect sound, bird sound, bird–human sound, insect–human sound, bird–insect sound, and silence. A dataset containing seven acoustic scenes was constructed, with 1000 samples for each scene. The requirements of the deep learning models on the training data volume and training epochs in the acoustic scene classification were evaluated through several sets of comparison experiments, and it was found that the models were able to achieve satisfactory accuracy when the training sample data volume for a single category was 600 and the training epochs were 100. To evaluate the generalization performance of different models to new data, a small test dataset was constructed, and multiple trained models were used to make predictions on the test dataset. All experimental results showed that the DenseNet_BC_34 model performs best among the comparison models, with an overall accuracy of 93.81% for the seven acoustic scenes on the validation dataset. This study provides practical experience for the application of deep learning techniques in urban sound monitoring and provides new perspectives and technical support for further exploring the relationship between human activities and biodiversity.
Open AccessClassification of Complicated Urban Forest Acoustic Scenes with Deep Learning Models
The use of passive acoustic monitoring (PAM) can compensate for the shortcomings of traditional survey methods on spatial and temporal scales and achieve all-weather and wide-scale assessment and prediction of environmental dynamics. Assessing the impact of human activities on biodiversity by analyzing the characteristics of acoustic scenes in the environment is a frontier hotspot in urban forestry. However, with the accumulation of monitoring data, the selection and parameter setting of the deep learning model greatly affect the content and efficiency of sound scene classification. This study compared and evaluated the performance of different deep learning models for acoustic scene classification based on the recorded sound data from Guangzhou urban forest. There are seven categories of acoustic scenes for classification: human sound, insect sound, bird sound, bird–human sound, insect–human sound, bird–insect sound, and silence. A dataset containing seven acoustic scenes was constructed, with 1000 samples for each scene. The requirements of the deep learning models on the training data volume and training epochs in the acoustic scene classification were evaluated through several sets of comparison experiments, and it was found that the models were able to achieve satisfactory accuracy when the training sample data volume for a single category was 600 and the training epochs were 100. To evaluate the generalization performance of different models to new data, a small test dataset was constructed, and multiple trained models were used to make predictions on the test dataset. All experimental results showed that the DenseNet_BC_34 model performs best among the comparison models, with an overall accuracy of 93.81% for the seven acoustic scenes on the validation dataset. This study provides practical experience for the application of deep learning techniques in urban sound monitoring and provides new perspectives and technical support for further exploring the relationship between human activities and biodiversity.
- Open Access
An Efficient Time-Domain End-to-End Single-Channel Bird Sound Separation Network
Bird sounds have obvious characteristics per species, and they are an important way for birds to communicate and transmit information. However, the recorded bird sounds in the field are usually mixed, which making it challenging to identify different bird species and to perform associated tasks. In this study, based on the supervised learning framework, we propose a bird sound separation network, a dual-path tiny transformer network, to directly perform end-to-end mixed species bird sound separation in the time-domain. This separation network is mainly composed of the dual-path network and the simplified transformer structure, which greatly reduces the computational resources required of the network. Experimental results show that our proposed separation network has good separation performance (SI-SNRi reaches 19.3 dB and SDRi reaches 20.1 dB), but compared with DPRNN and DPTNet, its parameters and floating point operations are greatly reduced, which means a higher separation efficiency and faster separation speed. The good separation performance and high separation efficiency indicate that our proposed separation network is valuable for distinguishing individual birds and studying the interaction between individual birds, as well as for realizing the automatic identification of bird species on a variety of mobile devices or edge computing devices.
Open AccessAn Efficient Time-Domain End-to-End Single-Channel Bird Sound Separation Network
Bird sounds have obvious characteristics per species, and they are an important way for birds to communicate and transmit information. However, the recorded bird sounds in the field are usually mixed, which making it challenging to identify different bird species and to perform associated tasks. In this study, based on the supervised learning framework, we propose a bird sound separation network, a dual-path tiny transformer network, to directly perform end-to-end mixed species bird sound separation in the time-domain. This separation network is mainly composed of the dual-path network and the simplified transformer structure, which greatly reduces the computational resources required of the network. Experimental results show that our proposed separation network has good separation performance (SI-SNRi reaches 19.3 dB and SDRi reaches 20.1 dB), but compared with DPRNN and DPTNet, its parameters and floating point operations are greatly reduced, which means a higher separation efficiency and faster separation speed. The good separation performance and high separation efficiency indicate that our proposed separation network is valuable for distinguishing individual birds and studying the interaction between individual birds, as well as for realizing the automatic identification of bird species on a variety of mobile devices or edge computing devices.