The influence of returnee technology executives on enterprise innovation: the innovation patent data of global exchange market listed companies

Lan, Xiao; Li, Zhe; Wang, Zongjun

doi:10.1080/1331677x.2022.2086600

Cited by 4 publications

(2 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The BLSTM model was introduced to realize the two-way memory of information.The contextual dependency information for acoustic features can be extracted through BLSTM. Both global and local features are beneficial to speech emotion recognition.Therefore, we combined CNN+BLSTM allowing the extraction of global and local features simultaneously [25]. The number of hidden cells in the BLSTM was set to 128.…”

Section: ) Feature Extractionmentioning

confidence: 99%

Speech Emotion Recognition Based on Transfer Emotion-Discriminative Features Subspace Learning

Kexin

Liu

2023

IEEE Access

View full text Add to dashboard Cite

Cross-corpus speech emotion recognition(SER) is a hot topic in emotion classification. Crosscorpus SER includes these four issues:feature selection, differences constraint, label regression and preservation of discriminative emotion features. Seldom literature can solve these four issues jointly in previous studies.In this work,we propose the transfer emotion-discriminative features subspace learning(TEDFSL) method.Acoustic features are extracted by the OpenSMILE in the source and target data. Then the extracted features are sent into CNN+BLSTM to learn higher-level global features and time series. The common low-dimensional subspace of the source data and target data is learned by Linear Discriminant analysis (LDA) to reduce the dimension and Maximum Mean Discrepancy (MMD) and Graph Embedding (GE) to constraint the differences between source data and target data. The common low-dimensional subspace is combined with the label regression matrix to learn the relationship between labels and features,after which the, DNN is selected as the final classifier to preserve emotion-discriminative features, emotion-aware center loss(l c ) is added and extensive experiments are carried out on cross-corpus SER tasks and the results demonstrate that our proposed method is superior to state-of-art cross-corpus SER.INDEX TERMS Cross-corpus speech emotion recognition, maximum mean discrepancy, graph embedding, label regression matrix, emotion-aware center loss.

show abstract

Section: ) Feature Extractionmentioning

confidence: 99%

Speech Emotion Recognition Based on Transfer Emotion-Discriminative Features Subspace Learning

Kexin

Liu

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Contextual dependencies information for acoustic features can be extracted through Bi-LSTM. Both global and local features are beneficial to speech emotion recognition, so we combined CNN+Bi-LSTM allowing the extraction of global and local features simultaneously [20]. The number of hidden cells in Bi-LSTM was set to 128.…”

Section: IImentioning

confidence: 99%

Cross-corpus bimodal speech emotion recognition

Liu

Kexin

2022

Preprint

View full text Add to dashboard Cite

Despite speech emotion recognition(SER) makes a significant contribution to artificial intelligence, there exists a heterogeneity gap between different modalities. Moreover, most cross-corpus SER only use audio modality. There are few studies on cross-corpus bimodal SER. Motivated by these problems, in this work, we address these issues at the same time. We design YouTube dataset as a source data and interactive emotional dyadic motion capture database (IEMOCAP) as a target data. In both source data and target data, we use CNN and bidirectional long short term memory network (Bi-LSTM) to extract speech features and use Bidirectional Encoder Representation from Transformers (BERT)+ Bi-LSTM to extract text features , then we design modality-invariance loss to form a common representation space of two modalities. To deal with the problem of cross-corpus SER, we learn a common subspace of source data and target data by optimizing Linear Discriminant analysis(LDA), Maximum Mean Discrepancy (MMD) and Graph Embedding (GE) jointly. To preserve emotion-discriminative features, we add emotion-aware center loss .We use SVM classifier as final emotion classification.The experiment results on IEMOCAP demonstrate that our method is superior to other state-of-art cross-corpus and bimodal SER.

show abstract

Building a Research Model for the Relationship Between Enterprise Innovation Values and Employees’ Innovation Behavior: With Innovation Self-efficacy as a Mediator

Yan,

Loang

2024

Studies in Systems, Decision and Control

View full text Add to dashboard Cite

The influence of returnee technology executives on enterprise innovation: the innovation patent data of global exchange market listed companies

Cited by 4 publications

References 48 publications

Speech Emotion Recognition Based on Transfer Emotion-Discriminative Features Subspace Learning

Speech Emotion Recognition Based on Transfer Emotion-Discriminative Features Subspace Learning

Cross-corpus bimodal speech emotion recognition

Building a Research Model for the Relationship Between Enterprise Innovation Values and Employees’ Innovation Behavior: With Innovation Self-efficacy as a Mediator

Contact Info

Product

Resources

About