@inproceedings{uroosa-etal-2026-speech,
title = "Speech-Based Emotion Recognition and Classification Integrating a {CNN} and {B}i{LSTM} Network",
author = "Uroosa, Fatima and
Abbas, Asim and
Zamir, Muhammad Tayyab and
Sidorov, Grigori",
editor = "Bagdon, Christopher and
Vishnubhotla, Krishnapriya and
Lindquist, Kristen A. and
Ungar, Lyle and
Klinger, Roman and
Mohammad, Saif M.",
booktitle = "Proceedings of Computational Affective Science ({CAS}) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.cas-1.3/",
doi = "10.63317/4tq9wz92ymg3",
pages = "29--37",
abstract = "Speech emotion recognition (SER) has gained significant interest in recent times, which utilizes speech signals to identify the emotional state of speakers. Accurate recognition of subtle emotional variations in speech, such as distinguishing closely related emotional states, remains a challenging problem due to the variability of speech signals and the acoustic similarity among emotion classes across different speakers and linguistic contexts. This paper proposes a hybrid deep learning model that integrates a Convolutional Neural Network (CNN) with a Bidirectional Long Short-Term Memory (BiLSTM) network to effectively identify both spectral and temporal features of speech. The log Mel-frequency spectral coefficients (MFSC) are used as input features to represent discriminative spectral representations, while the BiLSTM layer model represents long-range temporal dependencies in speech signals. The proposed framework is evaluated on the Toronto Emotional Speech Set (TESS), a publicly available dataset of acted emotional speech containing seven emotion classes. The experimental findings show that the hybrid CNN-BiLSTM achieved an overall classification accuracy of 96.36{\%}, significantly outperforming baseline models including GRU (91.84{\%}), BiLSTM (93.12{\%}), and CNN{--}GRU (94.67{\%}). These findings highlight the effectiveness of combining spectral and temporal modeling for improved speech emotion recognition performance. Furthermore, our CNN+BiLSTM approach offers a computationally efficient and data-efficient alternative to transformer-based models, while still effectively capturing both spatial and temporal emotional cues in speech, making it suitable for real-time and resource-constrained applications."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="uroosa-etal-2026-speech">
<titleInfo>
<title>Speech-Based Emotion Recognition and Classification Integrating a CNN and BiLSTM Network</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fatima</namePart>
<namePart type="family">Uroosa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asim</namePart>
<namePart type="family">Abbas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="given">Tayyab</namePart>
<namePart type="family">Zamir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Grigori</namePart>
<namePart type="family">Sidorov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Computational Affective Science (CAS) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Bagdon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Krishnapriya</namePart>
<namePart type="family">Vishnubhotla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kristen</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Lindquist</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lyle</namePart>
<namePart type="family">Ungar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Klinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saif</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Mohammad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Speech emotion recognition (SER) has gained significant interest in recent times, which utilizes speech signals to identify the emotional state of speakers. Accurate recognition of subtle emotional variations in speech, such as distinguishing closely related emotional states, remains a challenging problem due to the variability of speech signals and the acoustic similarity among emotion classes across different speakers and linguistic contexts. This paper proposes a hybrid deep learning model that integrates a Convolutional Neural Network (CNN) with a Bidirectional Long Short-Term Memory (BiLSTM) network to effectively identify both spectral and temporal features of speech. The log Mel-frequency spectral coefficients (MFSC) are used as input features to represent discriminative spectral representations, while the BiLSTM layer model represents long-range temporal dependencies in speech signals. The proposed framework is evaluated on the Toronto Emotional Speech Set (TESS), a publicly available dataset of acted emotional speech containing seven emotion classes. The experimental findings show that the hybrid CNN-BiLSTM achieved an overall classification accuracy of 96.36%, significantly outperforming baseline models including GRU (91.84%), BiLSTM (93.12%), and CNN–GRU (94.67%). These findings highlight the effectiveness of combining spectral and temporal modeling for improved speech emotion recognition performance. Furthermore, our CNN+BiLSTM approach offers a computationally efficient and data-efficient alternative to transformer-based models, while still effectively capturing both spatial and temporal emotional cues in speech, making it suitable for real-time and resource-constrained applications.</abstract>
<identifier type="citekey">uroosa-etal-2026-speech</identifier>
<identifier type="doi">10.63317/4tq9wz92ymg3</identifier>
<location>
<url>https://aclanthology.org/2026.cas-1.3/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>29</start>
<end>37</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Speech-Based Emotion Recognition and Classification Integrating a CNN and BiLSTM Network
%A Uroosa, Fatima
%A Abbas, Asim
%A Zamir, Muhammad Tayyab
%A Sidorov, Grigori
%Y Bagdon, Christopher
%Y Vishnubhotla, Krishnapriya
%Y Lindquist, Kristen A.
%Y Ungar, Lyle
%Y Klinger, Roman
%Y Mohammad, Saif M.
%S Proceedings of Computational Affective Science (CAS) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F uroosa-etal-2026-speech
%X Speech emotion recognition (SER) has gained significant interest in recent times, which utilizes speech signals to identify the emotional state of speakers. Accurate recognition of subtle emotional variations in speech, such as distinguishing closely related emotional states, remains a challenging problem due to the variability of speech signals and the acoustic similarity among emotion classes across different speakers and linguistic contexts. This paper proposes a hybrid deep learning model that integrates a Convolutional Neural Network (CNN) with a Bidirectional Long Short-Term Memory (BiLSTM) network to effectively identify both spectral and temporal features of speech. The log Mel-frequency spectral coefficients (MFSC) are used as input features to represent discriminative spectral representations, while the BiLSTM layer model represents long-range temporal dependencies in speech signals. The proposed framework is evaluated on the Toronto Emotional Speech Set (TESS), a publicly available dataset of acted emotional speech containing seven emotion classes. The experimental findings show that the hybrid CNN-BiLSTM achieved an overall classification accuracy of 96.36%, significantly outperforming baseline models including GRU (91.84%), BiLSTM (93.12%), and CNN–GRU (94.67%). These findings highlight the effectiveness of combining spectral and temporal modeling for improved speech emotion recognition performance. Furthermore, our CNN+BiLSTM approach offers a computationally efficient and data-efficient alternative to transformer-based models, while still effectively capturing both spatial and temporal emotional cues in speech, making it suitable for real-time and resource-constrained applications.
%R 10.63317/4tq9wz92ymg3
%U https://aclanthology.org/2026.cas-1.3/
%U https://doi.org/10.63317/4tq9wz92ymg3
%P 29-37
Markdown (Informal)
[Speech-Based Emotion Recognition and Classification Integrating a CNN and BiLSTM Network](https://aclanthology.org/2026.cas-1.3/) (Uroosa et al., CAS 2026)
ACL