LSSED: A Large-Scale Dataset and Benchmark for Speech Emotion Recognition

Fan, Weiquan; Xu, Xiangmin; Xing, Xiaofen; Chen, Weidong; Huang, Dongyan

doi:10.1109/icassp39728.2021.9414542

Cited by 24 publications

(8 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study has focused on the VGG-16 (with batch normalization) pre-trained computer vision model and we have highlighted efficient components for fine-tuning VGG-16 for emotional speech The work presented in this paper could be extended to include more pre-trained computer vision deep models such as ResNet (He et al, 2016), EfficientNet (Tan et Le, 2019), ViT (Dosovitskiy et al, 2020) and Inceptionv3 (GoogLeNet) (Szegedy et al, 2016). Besides, extensive experiments can be performed on other emotional datasets like LSSED (Fan et al, 2021), IEMOCAP (Busso et al, 2008), and RAVDESS (Livingstone et Russo, 2018) . Moreover, it could be interesting to include other modalities for emotional recognition like text, images and videos.…”

Section: Discussionmentioning

confidence: 99%

Emotional Speech Recognition with Pre-trained Deep Visual Models

Ragheb¹,

Mirzapour²,

Delfardi³

et al. 2022

Preprint

View full text Add to dashboard Cite

In this paper, we propose a new methodology for emotional speech recognition using visual deep neural network models. We employ the transfer learning capabilities of the pre-trained computer vision deep models to have a mandate for the emotion recognition in speech task. In order to achieve that, we propose to use a composite set of acoustic features and a procedure to convert them into images. Besides, we present a training paradigm for these models taking into consideration the different characteristics between acoustic-based images and regular ones. In our experiments, we use the pre-trained VGG-16 model and test the overall methodology on the Berlin EMO-DB dataset for speakerindependent emotion recognition. We evaluate the proposed model on the full list of the seven emotions and the results set a new state-of-the-art.

show abstract

Section: Discussionmentioning

confidence: 99%

Emotional Speech Recognition with Pre-trained Deep Visual Models

Ragheb¹,

Mirzapour²,

Delfardi³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…They used EMODB [61], a publicly available dataset that offers about 500 utterances with anger, boredom, disgust, fear, happiness, sadness, and neutral attitude. Fan et al proposed PyResNet to classify emotions from speech [51]. The name comes from modifying the second layer of the ResNet with pyramid convolution, which should reduce the issue of uncertain time position of accurate speech information.…”

Section: Machine Learning Models and Techniquesmentioning

confidence: 99%

Bringing Emotion Recognition Out of the Lab into Real Life: Recent Advances in Sensors and Machine Learning

Saganowski

2022

Electronics

View full text Add to dashboard Cite

Bringing emotion recognition (ER) out of the controlled laboratory setup into everyday life can enable applications targeted at a broader population, e.g., helping people with psychological disorders, assisting kids with autism, monitoring the elderly, and general improvement of well-being. This work reviews progress in sensors and machine learning methods and techniques that have made it possible to move ER from the lab to the field in recent years. In particular, the commercially available sensors collecting physiological data, signal processing techniques, and deep learning architectures used to predict emotions are discussed. A survey on existing systems for recognizing emotions in real-life scenarios—their possibilities, limitations, and identified problems—is also provided. The review is concluded with a debate on what challenges need to be overcome in the domain in the near future.

show abstract

“…However, angry, happy, neutral, and sad are selected in this paper. There are also many real-world corpora like LSSED [52], and so on.…”

Section: Data Preparationmentioning

confidence: 99%

Cross-corpus speech emotion recognition using subspace learning and domain adaption

Jia

Pai

2022

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

Speech emotion recognition (SER) is a hot topic in speech signal processing. When the training data and the test data come from different corpus, their feature distributions are different, which leads to the degradation of the recognition performance. Therefore, in order to solve this problem, a cross-corpus speech emotion recognition method is proposed based on subspace learning and domain adaptation in this paper. Specifically, training set data and the test set data are used to form the source domain and target domain, respectively. Then, the Hessian matrix is introduced to obtain the subspace for the extracted features in both source and target domains. In addition, an information entropy-based domain adaption method is introduced to construct the common space. In the common space, the difference between the feature distributions in the source domain and target domain is reduced as much as possible. To evaluate the performance of the proposed method, extensive experiments are conducted on cross-corpus speech emotion recognition. Experimental results show that the proposed method achieves better performance compared with some existing subspace learning and domain adaptation methods.

show abstract

LSSED: A Large-Scale Dataset and Benchmark for Speech Emotion Recognition

Cited by 24 publications

References 24 publications

Emotional Speech Recognition with Pre-trained Deep Visual Models

Emotional Speech Recognition with Pre-trained Deep Visual Models

Bringing Emotion Recognition Out of the Lab into Real Life: Recent Advances in Sensors and Machine Learning

Cross-corpus speech emotion recognition using subspace learning and domain adaption

Contact Info

Product

Resources

About