Speech emotion recognition using convolutional long short-term memory neural network and support vector machines

Kurpukdee, Nattapong; Koriyama, Tomoki; Kobayashi, Takao; Kasuriya, Sawit; Wutiwiwatchai, Chai; Lamsrichan, Poonlap

doi:10.1109/apsipa.2017.8282315

Cited by 24 publications

(8 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this model, a speech emotion recognition is proposed using convolutional long short-term memory (LSTM) and recurrent neural network (RNN) by using a phoneme-based feature extractor. This technique yields outputs phoneme-based emotion probabilities to all frames of an input utterance [22]. Now-a-days there is an increasing attentiveness to implement DL techniques to understand aspects from an emotional database.…”

Section: ) Feature Classification Using Convolutional Lstm-rnnmentioning

confidence: 99%

See 1 more Smart Citation

A Comparative Study On Speech Emotion Recognition

Sandesara

Parikh

Sapovadiya

et al. 2020

IJRESM

View full text Add to dashboard Cite

Today's world has been "Chatting" with the machines for a long time. With the first known research paper by Daellert et. al on this topic, we can say that discussions on Speech Emotion Recognition technology have been there for such a long time and have been evolving and increasing its applications in our life. Although worthy of these many applications, speech emotion recognition is a challenging task as emotion is a subjective thing. Not all humans are the same, each human deals differently with emotions. There are no common criteria or steps to categorize emotions. Forget computers, even we humans at times fail to read the emotions behind the other person. This paper provides the list of some speech emotion recognition methods and a glimpse of method used.

show abstract

Section: ) Feature Classification Using Convolutional Lstm-rnnmentioning

confidence: 99%

“…This model has only one LSTM layer comprising of nodes including the sigmoid activation function. During the result phase, the softmax activation function was taken into consideration for obtaining odds of 4 emotions, 36 phoneme-class based emotions, and 192 phoneme-based emotions respectively [22].…”

Section: On Considering Individual Parameters With Logisticmentioning

confidence: 99%

A Comparative Study On Speech Emotion Recognition

Sandesara

Parikh

Sapovadiya

et al. 2020

IJRESM

View full text Add to dashboard Cite

show abstract

“…This resulted in 40 features that were then orthogonalised by a PCA. We used the architecture proposed in [17], and improved it by employing a variable network depth. For the training, we implemented a dropout layer after each block and a sparsity constraint.…”

Section: Feature Processingmentioning

confidence: 99%

Employing Bottleneck and Convolutional Features for Speech-Based Physical Load Detection on Limited Data Amounts

Egorow¹,

Mrech²,

Weißkirchen³

et al. 2019

Interspeech 2019

View full text Add to dashboard Cite

The detection of different levels of physical load from speech has many applications: Besides telemedicine, non-contact detection of certain heart rate ranges can be useful for sports and other leisure time devices. Available approaches mainly use a high number of spectral and prosodic features. In this setting of typically small data sets, such as the Talk & Run data set and the Munich Biovoice Corpus, the high-dimensional feature spaces are only sparsely populated. Therefore, we aim at a reduction of the feature number using modern neural net inspired features: Bottleneck layer features, obtained from standard low-level descriptors via a feed-forward neural network, and activation map features, obtained from spectrograms via a convolutional neural network. We use these features for an SVM classification of high and low physical load and compare their performance. We also discuss the possibility of hyperparameter transfer of the extracting networks between different data sets. We show that even for limited amounts of data, deep learning based methods can bring a substantial improvement over "conventional" features.

show abstract

“…In contrast, we addressed the low-accuracy issues and proposed a novel framework for the emotion recognition that utilized speech signals. We designed a system which recognized the local hidden emotional cues in the raw speech signal by utilizing the hierarchical ConvLSTM blocks [17]. We adopted two types of sequential learning in this framework.…”

Section: Introductionmentioning

confidence: 99%

CLSTM: Deep Feature-Based Speech Emotion Recognition Using the Hierarchical ConvLSTM Network

2020

View full text Add to dashboard Cite

Artificial intelligence, deep learning, and machine learning are dominant sources to use in order to make a system smarter. Nowadays, the smart speech emotion recognition (SER) system is a basic necessity and an emerging research area of digital audio signal processing. However, SER plays an important role with many applications that are related to human–computer interactions (HCI). The existing state-of-the-art SER system has a quite low prediction performance, which needs improvement in order to make it feasible for the real-time commercial applications. The key reason for the low accuracy and the poor prediction rate is the scarceness of the data and a model configuration, which is the most challenging task to build a robust machine learning technique. In this paper, we addressed the limitations of the existing SER systems and proposed a unique artificial intelligence (AI) based system structure for the SER that utilizes the hierarchical blocks of the convolutional long short-term memory (ConvLSTM) with sequence learning. We designed four blocks of ConvLSTM, which is called the local features learning block (LFLB), in order to extract the local emotional features in a hierarchical correlation. The ConvLSTM layers are adopted for input-to-state and state-to-state transition in order to extract the spatial cues by utilizing the convolution operations. We placed four LFLBs in order to extract the spatiotemporal cues in the hierarchical correlational form speech signals using the residual learning strategy. Furthermore, we utilized a novel sequence learning strategy in order to extract the global information and adaptively adjust the relevant global feature weights according to the correlation of the input features. Finally, we used the center loss function with the softmax loss in order to produce the probability of the classes. The center loss increases the final classification results and ensures an accurate prediction as well as shows a conspicuous role in the whole proposed SER scheme. We tested the proposed system over two standard, interactive emotional dyadic motion capture (IEMOCAP) and ryerson audio visual database of emotional speech and song (RAVDESS) speech corpora, and obtained a 75% and an 80% recognition rate, respectively.

show abstract

Speech emotion recognition using convolutional long short-term memory neural network and support vector machines

Cited by 24 publications

References 12 publications

A Comparative Study On Speech Emotion Recognition

A Comparative Study On Speech Emotion Recognition

Employing Bottleneck and Convolutional Features for Speech-Based Physical Load Detection on Limited Data Amounts

CLSTM: Deep Feature-Based Speech Emotion Recognition Using the Hierarchical ConvLSTM Network

Contact Info

Product

Resources

About