Search for: All records

The Interspeech 2025 speech emotion recognition in natural istic conditions challenge builds on previous efforts to advance speech emotion recognition (SER) in real-world scenarios. The focus is on recognizing emotions from spontaneous speech, moving beyond controlled datasets. It provides a framework for speaker-independent training, development, and evaluation, with annotations for both categorical and dimensional tasks. The challenge attracted 93 research teams, whose models significantly improved state-of-the-art results over competitive baselines. This paper summarizes the challenge, focusing on the key outcomes. We analyze top-performing methods, emerging trends, and innovative directions. We highlight the effectiveness of combining foundational models based on audio and text to achieve robust SER systems. The competition website, with leaderboards, baseline code, and instructions, is available at: https://lab-msp.com/MSP-Podcast_Competition/IS2025/. 

Emotion recognition is inherently a multimodal problem. Humans use both audible and visual cues to determine a person’s emotions. There has been extensive improvement in the methods we use to fuse audio and visual representations between two unimodal deep-learning models. However, there is a lack of accommodation for modalities that have a disparity in the amount of computational resources needed to provide the same amount of temporal information. As the sequence length increases, current methods often make simplifications such as discarding frames or cropping the sequence. This paper introduces a chunking methodology designed for cross-attention-based multimodal transformer architectures. The approach involves segmenting the visual input—the more computationally demanding modality—into chunks. Cross-attention is then performed between the encoded audio and visual features instead of the original sequence lengths of the unimodal backbones. Our method achieves significant improvements over conventional cross-attention techniques in the audio-visual domain for a six-class emotional recognition problem, demonstrating better F1 score, precision, and recall on the CREMA-D database while reducing computational overhead. 

Most existing audio-text emotion recognition studies have focused on the computational modeling aspects, including strategies for fusing the modalities. An area that has received less attention is understanding the role of proper temporal synchronization between the modalities in the model performance. This study presents a transformer-based model designed with a word-chunk concept, which offers an ideal framework to explore different strategies to align text and speech. The approach creates chunks with alternative alignment strategies with different levels of dependency on the underlying lexical boundaries. A key contribution of this study is the multi-scale chunk alignment strategy, which generates random alignments to create the chunks without considering lexical boundaries. For every epoch, the approach generates a different alignment for each sentence, serving as an effective regularization method for temporal dependency. Our experimental results based on the MSP-Podcast corpus indicate that providing precise temporal alignment information to create the audio-text chunks does not improve the performance of the system. The attention mechanisms in the transformer-based approach are able to compensate for imperfect synchronization between the modalities. However, using exact lexical boundaries makes the system highly vulnerable to missing modalities. In contrast, the model trained with the proposed multi-scale chunk regularization strategy using random alignment can significantly increase its robustness against missing data and remain effective, even under a single audio-only emotion recognition task. The code is available at: https://github.com/winston-lin-wei-cheng/MultiScale-Chunk-Regularization 

Representation learning is a challenging, but essential task in audiovisual learning. A key challenge is to generate strong cross-modal representations while still capturing discriminative information contained in unimodal features. Properly capturing this information is important to increase accuracy and robustness in audio-visual tasks. Focusing on emotion recognition, this study proposes novel cross-modal ladder networks to capture modality-specific in-formation while building strong cross-modal representations. Our method utilizes representations from a backbone network to implement unsupervised auxiliary tasks to reconstruct intermediate layer representations across the acoustic and visual networks. The skip connections between the cross-modal encoder and decoder provide powerful modality-specific and multimodal representations for emotion recognition. Our model on the CREMA-D corpus achieves high performance with precision, recall, and F1 scores over 80% on a six-class problem. 

The uncertainty in modeling emotions makes speech emotion recognition (SER) systems less reliable. An intuitive way to increase trust in SER is to reject predictions with low confidence. This approach assumes that an SER system is well calibrated, where highly confident predictions are often right and low confident predictions are often wrong. Hence, it is desirable to calibrate the confidence of SER classifiers. We evaluate the reliability of SER systems by exploring the relationship between confidence and accuracy, using the expected calibration error (ECE) metric. We develop a multi-label variant of the post-hoc temperature scaling (TS) method to calibrate SER systems, while preserving their accuracy. The best method combines an emotion co-occurrence weight penalty function, a class-balanced objective function, and the proposed multi-label TS calibration method. The experiments show the effectiveness of our developed multi-label calibration method in terms of ac- curacy and ECE. 

Speech Emotion Recognition (SER) faces a distinct challenge compared to other speech-related tasks because the annotations will show the subjective emotional perceptions of different annotators. Previous SER studies often view the subjectivity of emotion perception as noise by using the majority rule or plurality rule to obtain the consensus labels. However, these standard approaches overlook the valuable information of labels that do not agree with the consensus and make it easier for the test set. Emotion perception can have co-occurring emotions in realistic conditions, and it is unnecessary to regard the disagreement between raters as noise. To bridge the SER into a multi-label task, we introduced an “all-inclusive rule,” which considers all available data, ratings, and distributional labels as multi-label targets and a complete test set. We demonstrated that models trained with multi-label targets generated by the proposed AR outperform conventional single-label methods across incomplete and complete test sets. 

Audio-visual emotion recognition (AVER) has been an important research area in human-computer interaction (HCI). Traditionally, audio-visual emotional datasets and corresponding models derive their ground truths from annotations obtained by raters after watching the audio-visual stimuli. This conventional method, however, neglects the nuanced human perception of emotional states, which varies when annotations are made under different emotional stimuli conditions—whether through unimodal or multimodal stimuli. This study investigates the potential for enhanced AVER system performance by integrating diverse levels of annotation stimuli, reflective of varying perceptual evaluations. We propose a two-stage training method to train models with the labels elicited by audio-only, face-only, and audio-visual stimuli. Our approach utilizes different levels of annotation stimuli according to which modality is present within different layers of the model, effectively modeling annotation at the unimodal and multi-modal levels to capture the full scope of emotion perception across unimodal and multimodal contexts. We conduct the experiments and evaluate the models on the CREMA-D emotion database. The proposed methods achieved the best performances in macro-/weighted-F1 scores. Additionally, we measure the model calibration, performance bias, and fairness metrics considering the age, gender, and race of the AVER systems. 

The field of speech emotion recognition (SER) aims to create scientifically rigorous systems that can reliably characterize emotional behaviors expressed in speech. A key aspect for building SER systems is to obtain emotional data that is both reliable and reproducible for practitioners. However, academic researchers encounter difficulties in accessing or collecting naturalistic, large-scale, reliable emotional recordings. Also, the best practices for data collection are not necessarily described or shared when presenting emotional corpora. To address this issue, the paper proposes the creation of an affective naturalistic database consortium (AndC) that can encourage multidisciplinary cooperation among researchers and practitioners in the field of affective computing. This paper’s contribution is twofold. First, it proposes the design of the AndC with a customizable-standard framework for intelligently-controlled emotional data collection. The focus is on leveraging naturalistic spontaneous record- ings available on audio-sharing websites. Second, it presents as a case study the development of a naturalistic large-scale Taiwanese Mandarin podcast corpus using the customizable- standard intelligently-controlled framework. The AndC will en- able research groups to effectively collect data using the provided pipeline and to contribute with alternative algorithms or data collection protocols. 

Speech emotion recognition (SER) is a challenging task due to the limited availability of real-world labeled datasets. Since it is easier to find unlabeled data, the use of self-supervised learning (SSL) has become an attractive alternative. This study proposes new pre-text tasks for SSL to improve SER. While our target application is SER, the proposed pre-text tasks include audio-visual formulations, leveraging the relationship between acoustic and facial features. Our proposed approach introduces three new unimodal and multimodal pre-text tasks that are carefully designed to learn better representations for predicting emotional cues from speech. Task 1 predicts energy variations (high or low) from a speech sequence. Task 2 uses speech features to predict facial activation (high or low) based on facial landmark movements. Task 3 performs a multi-class emotion recognition task on emotional labels obtained from combinations of action units (AUs) detected across a video sequence. We pre-train a network with 60.92 hours of unlabeled data, fine-tuning the model for the downstream SER task. The results on the CREMA-D dataset show that the model pre-trained on the proposed domain-specific pre-text tasks significantly improves the precision (up to 5.1%), recall (up to 4.5%), and F1-scores (up to 4.9%) of our SER system.