The DOI matches its Crossref record; 50 of the 50 references it cites were found in a registry or an index.
Dawn of the Transformer Era in Speech Emotion Recognition: Closing the Valence Gap
Open accessAbstract
Recent advances in transformer-based architectures have shown promise in several machine learning tasks. In the audio domain, such architectures have been successfully utilised in the field of speech emotion recognition (SER). However, existing works have not evaluated the influence of model size and pre-training data on downstream performance, and have shown limited attention to generalisation, robustness, fairness, and efficiency. The present contribution conducts a thorough analysis of these aspects on several pre-trained variants of wav2vec 2.0 and HuBERT that we fine-tuned on the dimensions arousal, dominance, and valence of MSP-Podcast, while additionally using IEMOCAP and MOSI to test cross-corpus generalisation. To the best of our knowledge, we obtain the top performance for valence prediction without use of explicit linguistic information, with a concordance correlation coefficient (CCC) of. 638 on MSP-Podcast. Our investigations reveal that transformer-based architectures are more robust compared to a CNN-based baseline and fair with respect to gender groups, but not towards individual speakers. Finally, we show that their success on valence is based on implicit linguistic information, which explains why they perform on-par with recent multimodal approaches that explicitly utilise textual information. To make our findings reproducible, we release the best performing model to the community.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
An argument for basic emotions
Ekman, P. (1992) · Cognition and Emotion · doi:10.1080/02699939208411068 · Cited by 9,646 · cited 1×
“SER research is dominated by two conceptual paradigms: discrete emotions [2] and emotional dimensions [3].”
BackgroundA concordance correlation coefficient to evaluate reproducibility.
Lin, L. I.-K. (1989) · Biometrics · doi:10.2307/2532051 · Cited by 8,785
Han (2023) · doi:10.1109/tpami.2022.3152247 · Cited by 4,682
IEMOCAP: Interactive emotional dyadic motion capture database
Busso, C., Bulut, M., Lee, C.-C., Kazemzadeh, A., Mower, E., Kim, S., Chang, J. N., Lee, S., & Narayanan, S. S. (2008) · Language Resources and Evaluation · doi:10.1007/s10579-008-9076-6 · Cited by 3,869
HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units
Hsu, W.-N., Bolte, B., Tsai, Y.-H. H., Lakhotia, K., Salakhutdinov, R., & Mohamed, A. (2021) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2021.3122291 · Cited by 2,983
A Survey of Affect Recognition Methods: Audio, Visual, and Spontaneous Expressions
Zeng, Z., Pantic, M., Roisman, G. I., & Huang, T. S. (2009) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2008.52 · Cited by 2,797
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676
Evidence for a three-factor theory of emotions
Russell, J. A., & Mehrabian, A. (1977) · Journal of Research in Personality · doi:10.1016/0092-6566(77)90037-x · Cited by 1,940 · cited 2×
“The first investigates emotional categories like happy or sad, while the latter focuses on the dimensions of arousal, valence, and dominance [3].”
BackgroundAffect Detection: An Interdisciplinary Review of Models, Methods, and Their Applications
Calvo, R. A., & D'Mello, S. (2010) · IEEE Transactions on Affective Computing · doi:10.1109/t-affc.2010.1 · Cited by 1,893 · cited 2×
“Paralinguistics works better for arousal and dominance [5, 6, 7, 8] and has the potential to generalise across different languages, while typically suffering from low valence performance [4, 8].”
BackgroundESC: Dataset for Environmental Sound Classification
Piczak, K. J. (2015) · Proceedings of the 23rd ACM international conference on Multimedia · doi:10.1145/2733373.2806390 · Cited by 1,397
PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition
Kong, Q., Cao, Y., Iqbal, T., Wang, Y., Wang, W., & Plumbley, M. D. (2020) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2020.3030497 · Cited by 1,235
Adieu features? End-to-end speech emotion recognition using a deep convolutional recurrent network
Trigeorgis, G., Ringeval, F., Brueckner, R., Marchi, E., Nicolaou, M. A., Schuller, B., & Zafeiriou, S. (2016) · 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2016.7472669 · Cited by 904
Self-citationMachine Learning Testing: Survey, Landscapes and Horizons
Zhang, J. M., Harman, M., Ma, L., & Liu, Y. (2022) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2019.2962027 · Cited by 897
Multimodal Sentiment Intensity Analysis in Videos: Facial Gestures and Verbal Messages
Zadeh, A., Zellers, R., Pincus, E., & Morency, L.-P. (2016) · IEEE Intelligent Systems · doi:10.1109/mis.2016.94 · Cited by 852
SUPERB: Speech Processing Universal PERformance Benchmark
Yang, S.-W., Chi, P.-H., Chuang, Y.-S., Lai, C.-I. J., Lakhotia, K., Lin, Y. Y., Liu, A. T., Shi, J., Chang, X., Lin, G.-T., et al. (2021) · Interspeech 2021 · doi:10.21437/interspeech.2021-1775 · Cited by 681
XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale
Babu, A., Wang, C., Tjandra, A., Lakhotia, K., Xu, Q., Goyal, N., Singh, K., von Platen, P., Saraf, Y., Pino, J., et al. (2022) · Interspeech 2022 · doi:10.21437/interspeech.2022-143 · Cited by 586
Speech emotion recognition: two decades in a nutshell, benchmarks, and ongoing trends
Schuller, B. W. (2018) · Communications of the ACM · doi:10.1145/3129340 · Cited by 541
Self-citationRingeval, F., Schuller, B., Valstar, M., Cummins, N., Cowie, R., Tavabi, L., Schmitt, M., Alisamir, S., Amiriparian, S., Messner, E.-M., et al. (2019) · Proceedings of the 9th International on Audio/Visual Emotion Challenge and Workshop · doi:10.1145/3347320.3357688 · Cited by 409
Self-citationUnderspecification Presents Challenges for Credibility in Modern Machine Learning
D'Amour, A., Heller, K., Moldovan, D., Adlam, B., Alipanahi, B., Beutel, A., Chen, C., Deaton, J., Eisenstein, J., Hoffman, M. D., et al. (2020) · arXiv · doi:10.48550/arxiv.2011.03395 · Cited by 398 · cited 1×
“This could be a manifestation of the underspecification phenomenon plaguing machine learning architectures [62], as models which have similar performance on the entire test set, nevertheless behave differently across different subsets of it.”
Doddington, G., Liggett, W., Martin, A., Przybocki, M., & Reynolds, D. A. (1998) · 5th International Conference on Spoken Language Processing (ICSLP 1998) · doi:10.21437/icslp.1998-244 · Cited by 396
Emotion Recognition from Speech Using wav2vec 2.0 Embeddings
Pepino, L., Riera, P., & Ferrer, L. (2021) · Interspeech 2021 · doi:10.21437/interspeech.2021-703 · Cited by 389
Are they different? Affect, feeling, emotion, sentiment, and opinion detection in text
Munezero, M., Montero, C. S., Sutinen, E., & Pajunen, J. (2014) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2014.2317187 · Cited by 374
Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders
Liu, A. T., Yang, S.-W., Chi, P.-H., Hsu, P.-C., & Lee, H.-Y. (2020) · ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp40776.2020.9054458 · Cited by 337
Lotfian, R., & Busso, C. (2019) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2017.2736999 · Cited by 329
Wang, C., Riviere, M., Lee, A., Wu, A., Talnikar, C., Haziza, D., Williamson, M., Pino, J., & Dupoux, E. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.80 · Cited by 329
Personalized machine learning for robot perception of affect and engagement in autism therapy
Rudovic, O., Lee, J., Dai, M., Schuller, B., & Picard, R. W. (2018) · Science Robotics · doi:10.1126/scirobotics.aao6760 · Cited by 316
Self-citationSewa db: A rich database for audio-visual emotion and sentiment research in the wild
Kossaifi, J., Walecki, R., Panagakis, Y., Shen, J., Schmitt, M., Ringeval, F., Han, J., Pandit, V., Toisoul, A., Schuller, B., et al. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2944808 · Cited by 243
Self-citationRobust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training
Hsu, W.-N., Sriram, A., Baevski, A., Likhomanenko, T., Xu, Q., Pratap, V., Kahn, J., Lee, A., Collobert, R., Synnaeve, G., et al. (2021) · Interspeech 2021 · doi:10.21437/interspeech.2021-236 · Cited by 182
AVEC 2018 Workshop and Challenge
Ringeval, F., Schuller, B. W., Valstar, M., Cowie, R., Kaya, H., Schmitt, M., Amiriparian, S., Cummins, N., Lalanne, D., Michaud, A., et al. (2018) · doi:10.1145/3266302.3266316 · Cited by 162
Self-citationSurvey on bimodal speech emotion recognition from acoustic and linguistic information fusion
Atmaja, B. T., Sasou, A., & Akagi, M. (2022) · Speech Communication · doi:10.1016/j.specom.2022.03.002 · Cited by 142
Multimodal Emotion Recognition with High-Level Speech and Text Features
Makiuchi, M. R., Uto, K., & Shinoda, K. (2021) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru51503.2021.9688036 · Cited by 116
Polarity and Intensity: the Two Aspects of Sentiment Analysis
Tian, L., Lai, C., & Moore, J. D. (2018) · doi:10.18653/v1/w18-3306 · Cited by 77
Towards Robust Speech Emotion Recognition Using Deep Residual Networks for Speech Enhancement
Triantafyllopoulos, A., Keren, G., Wagner, J., Steiner, I., & Schuller, B. W. (2019) · Interspeech (USB) · doi:10.21437/interspeech.2019-1811 · Cited by 77
Self-citationContrastive Unsupervised Learning for Speech Emotion Recognition
Li, M., Yang, B., Levy, J., Stolcke, A., Rozgić, V., Matsoukas, S., Papayiannis, C., Bone, D., & Wang, C. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9413910 · Cited by 76
Fusion Approaches for Emotion Recognition from Speech Using Acoustic and Text-Based Features
Pepino, L., Riera, P., Ferrer, L., & Gravano, A. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9054709 · Cited by 62
Ethics and Good Practice in Computational Paralinguistics
Batliner, A. M., Hantke, S., & Schuller, B. W. (2020) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2020.3021015 · Cited by 53
Self-citationSahu, S., Mitra, V., Seneviratne, N., & Espy-Wilson, C. (2019) · Interspeech (USB) · doi:10.21437/interspeech.2019-1149 · Cited by 52
Deep speaker conditioning for speech emotion recognition
Triantafyllopoulos, A., Liu, S., & Schuller, B. W. (2021) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme51207.2021.9428217 · Cited by 49
Self-citationCopyPaste: An Augmentation Method for Speech Emotion Recognition
Pappagari, R. R., Villalba, J., Żelasko, P., Moro-Velázquez, L., & Dehak, N. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9415077 · Cited by 46
A General Framework for Fair Regression
Fitzsimons, J., Ali, A. A., Osborne, M., & Roberts, S. (2019) · Entropy · doi:10.3390/e21080741 · Cited by 45
Gender De-Biasing in Speech Emotion Recognition
Gorrostieta, C., Lotfian, R., Taylor, K. M., Brutti, R. A., & Kane, J. (2019) · Interspeech (USB) · doi:10.21437/interspeech.2019-1708 · Cited by 40
Cheong, J., Kalkan, S., & Güneş, H. (2021) · IEEE Signal Processing Magazine · doi:10.1109/msp.2021.3106619 · Cited by 38
Probing speech emotion recognition transformers for linguistic knowledge
Triantafyllopoulos, A., Wagner, J., Wierstorf, H., Schmitt, M., Reichel, U. D., Eyben, F., Burkhardt, F., & Schuller, B. W. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-10371 · Cited by 34
Self-citationTriantafyllopoulos, A., & Schuller, B. W. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414896 · Cited by 32
Self-citationSridhar, K., & Busso, C. (2022) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2022.3187336 · Cited by 31
Using Large Pre-Trained Models with Cross-Modal Attention for Multi-Modal Emotion RecognitionPreprint
N, K. D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.09669 · Cited by 18
The Perception of Emotions in Noisified Nonsense Speech
Parada‐Cabaleiro, E., Baird, A., Batliner, A. M., Cummins, N., Hantke, S., & Schuller, B. W. (2017) · Interspeech (USB) · doi:10.21437/interspeech.2017-104 · Cited by 14
Self-citationRobust Speech Emotion Recognition Under Different Encoding Conditions
Oates, C., Triantafyllopoulos, A., Steiner, I., & Schuller, B. W. (2019) · Interspeech (USB) · doi:10.21437/interspeech.2019-1658 · Cited by 12
Self-citation
Research works printed but not linked: 9
- chen, 2020, A simple framework for contrastive learning of visual representations, Proc Int Conf Mach Learn, 1597
- corbett-davies, 2018, The measure and mismeasure of fairness: A critical review of fair machine learning
- vaswani, 2017, Attention is all you need, Proc Adv Neural Inf Process Syst, 5998
- baevski, 2020, wav2vec 2.0: A framework for self-supervised learning of speech representations, Proc Adv Neural Inf Process Syst, 12449
- 10.1007/978-3-319-73706-5_2 · DOI
- erhan, 2010, Why does unsupervised pre-training help deep learning?, Proc 13th Int Conf Artif Intell Statist, 201
- van der maaten, 2008, Visualizing data using t-SNE, J Mach Learn Res, 9, 2579
- 10.1109/TAFFC.2021. 3114365 · doi:10.1109/taffc.2021
- neyshabur, 2020, What is being transferred in transfer learning?, Proc Adv Neural Inf Process Syst, 512
Cited by
Long Dialogue Emotion Detection Based on Commonsense Knowledge Graph Guidance
Nie, W., Bao, Y., Zhao, Y., & Liu, A. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3267295 · Cited by 96
Personalised depression forecasting using mobile sensor data and ecological momentary assessment
Kathan, A., Harrer, M., Küster, L., Triantafyllopoulos, A., He, X., Milling, M., Gerczuk, M., Yan, T., Rajamani, S. T., Heber, E., et al. (2022) · Frontiers in Digital Health · doi:10.3389/fdgth.2022.964582 · Cited by 47
Self-citationFeng, T., & Narayanan, S. (2023) · 2023 11th International Conference on Affective Computing and Intelligent Interaction (ACII) · doi:10.1109/acii59096.2023.10388152 · Cited by 34
“More recently, [6] conducted a comprehensive analysis of fine-tuning Wav2vec 2.0 and HuBERT [10] for SER.”
MethodInfluentialChou, H.-C., Goncalves, L., Leem, S.-G., Salman, A. N., Lee, C.-C., & Busso, C. (2025) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2024.3411290 · Cited by 22
Metadata
- Authors
- Wagner, J., Triantafyllopoulos, A., Wierstorf, H., Schmitt, M., Burkhardt, F., Eyben, F., & Schuller, B. W.
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2023-09-01
- Volume
- 45
- Issue
- 9
- Pages
- 10745-10759
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W4221145199
- Cited by
- 395
- References
- 50
- FWCI
- 87.54
- Type
- journal article
- Language
- en
- Open access
- green
- Licence
- Funders
- DFG's Reinhart Koselleck (442218748)
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.