Automatic speech emotion recognition using recurrent neural networks with local attention

By Seyedmahdad Mirsamadi, Emad Barsoum, Cha Zhang. IEEE International Conference on Acoustics, Speech, and Signal Processing, 2017

670 citations recorded by the source corpus.

Subfields: Experimental and Cognitive Psychology, Signal Processing

View Paper: https://www.semanticscholar.org/paper/b44b751db2b6f6ef662f517e9a01e055c6e337a8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Experimental and Cognitive Psychology

1. Leonardo Pepino
2. Luciana Ferrer
3. Seunghyun Yoon
4. Ivan Marsic
5. Kristof Van Laerhoven
6. Syed Asif Ahmad Qadri
7. Taiba Maijd Wani
8. Kyomin Jung

In Signal Processing

1. Ne Luo
2. Wubo Li
3. Wei Zou
4. Dongwei Jiang
5. Xiangang Li
6. Leonardo Pepino
7. Luciana Ferrer
8. Seunghyun Yoon

Citations in the corpus

• A Systematic Review on Affective Computing: Emotion Models, Databases, and Recent Advances (2022, methodology): “[198] introduced an attention model with weighted time-pooling strategy into the RNN to more emotionally salient regions.”
• Didispeech: A Large Scale Mandarin Speech Corpus (2020, background): “Powered by the emerging technology on deep learning, rapid progress has been made on the key technologies in speech processing [1, 2], including automatic speech recognition (ASR) [3, 4, 5, 6], text-to-speech (TTS) [1, 2, 7], speaker identification (SID) [8, 9], speech emotion recognition [10, 11, 1”
• Multimodal Affective Analysis Using Hierarchical Attention Strategy with Word-Level Alignment (2018, background): “Recent approaches introduce attention mechanisms to focus the models on informative words (Yang et al., 2016) and attentive audio frames (Mirsamadi et al., 2017) for each individual modality.”
• Multimodal Speech Emotion Recognition Using Audio and Text (2018, methodology): “Motivated by the architecture used in [25, 26], we build an audio recurrent encoder (ARE) to predict the class of a given audio signal.”
• Survey on Deep Neural Networks in Speech and Vision Systems (2019, background): “[138] have used a deep recurrent network with local attention to automatically learn speech features from audio signals.”
• Emotion Recognition from Speech Using Wav2vec 2.0 Embeddings (2021, background): “BiLSTM w. attention [13] 58.8 - CNN-BiLSTM [14] 59.4 - TDNN-LSTM w. attention [15] 60.7 - Wav2Vec [27] 64.3 - Table 2 also shows some of the results obtained in other works on the IEMOCAP dataset, using the same experimental setup we are using.”
• Databases, features and classifiers for speech emotion recognition: a review (2018, methodology): “Mirsamadi et al. (2017) utilized the deep learning to automatically discover emotionally relevant features from Analyzing the relation between emotional state of the speaker and glottal activity Gangamohan et al. (2014) Excitation source signal Two features strength of excitation and Spectral band…”
• A Comprehensive Review of Speech Emotion Recognition Systems (2021, background): “In [69], it was depicted that RNN can learn temporal aggregation and frame-level characterization over a long period.”
• Introducing WESAD, a Multimodal Dataset for Wearable Stress and Affect Detection (2018, background): “Using deep neural networks, trained on audio and/or visual data, a high performance in emotion classification is achieved [17, 29].”