Search for: All records

Unsupervised domain adaptation offers significant potential for cross-lingual speech emotion recognition (SER). Most relevant studies have addressed this problem as a domain mismatch without considering phonetical emotional differences across languages. Our study explores universal discrete speech units obtained with vector quantization of wavLM representations from emotional speech in English, Taiwanese Mandarin, and Russian. We estimate cluster-wise distributions of quantized wavLM frames to quantify phonetic commonalities and differences across languages, vowels, and emotions. Our findings indicate that certain emotion-specific phonemes exhibit cross-linguistic similarities. The distribution of vowels varies with emotional content. Certain vowels across languages show close distributional proximity, offering anchor points for cross-lingual domain adaptation. We also propose and validate a method to quantify phoneme distribution similarities across languages. 

Building speech emotion recognition (SER) models for low-resource languages is challenging due to the scarcity of labeled speech data. This limitation mandates the development of cross-lingual unsupervised domain adaptation techniques to effectively utilize labeled data from resource-rich languages. Inspired by the TransVQA framework, we propose a method that leverages a shared quantized feature space to enable knowledge transfer between labeled and unlabeled data across languages. The approach utilizes a quantized codebook to capture shared features, while reducing the domain gap, and aligning class distributions, thereby improving classification accuracy. Additionally, an information loss (InfoLoss) mechanism mitigates critical information loss during quantization. InfoLoss achieves this goal by minimizing the loss within the simplex of posterior class label distributions. The proposed method demonstrates superior performance compared to state-of-the-art baseline approaches. Index Terms: Speech Emotion Recognition, Cross-lingual Unsupervised Domain Adaptation, Discrete Features, InfoLoss 

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/. 

The prevalence of cross-lingual speech emotion recognition (SER) modeling has significantly increased due to its wide range of applications. Previous studies have primarily focused on technical strategies to adapt features, domains, and labels across languages, often overlooking the underlying universalities between the languages. In this study, we address the language adaptation challenge in cross-lingual scenarios by incorporating vowel-phonetic constraints. Our approach is structured in two main parts. Firstly, we investigate the vowel-phonetic commonalities associated with specific emotions across languages, particularly focusing on common vowels that prove to be valuable for SER modeling. Secondly, we utilize these identified common vowels as anchors to facilitate cross-lingual SER. To demonstrate the effectiveness of our approach, we conduct case studies using American English, Taiwanese Mandarin, and Russian using three naturalistic emotional speech corpora: the MSP-Podcast, BIIC-Podcast, and Dusha corpora. The proposed unsupervised cross-lingual SER model, leveraging this phonetic information, surpasses the performance of the baselines. This research provides insights into the importance of considering phonetic similarities across languages for effective language adaptation in cross-lingual SER scenarios. 

Recent studies have demonstrated the effectiveness of fine-tuning self-supervised speech representation models for speech emotion recognition (SER). However, applying SER in real-world environments remains challenging due to pervasive noise. Relying on low-accuracy predictions due to noisy speech can undermine the user’s trust. This paper proposes a unified self-supervised speech representation framework for enhanced speech emotion recognition designed to increase noise robustness in SER while generating enhanced speech. Our framework integrates speech enhancement (SE) and SER tasks, leveraging shared self-supervised learning (SSL)-derived features to improve emotion classification performance in noisy environments. This strategy encourages the SE module to enhance discriminative information for SER tasks. Additionally, we introduce a cascade unfrozen training strategy, where the SSL model is gradually unfrozen and fine-tuned alongside the SE and SER heads, ensuring training stability and preserving the generalizability of SSL representations. This approach demonstrates improvements in SER performance under unseen noisy conditions without compromising SE quality. When tested at a 0 dB signal-to-noise ratio (SNR) level, our proposed method outperforms the original baseline by 3.7% in F1-Macro and 2.7% in F1-Micro scores, where the differences are statistically significant. 

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. 

The advancement of Speech Emotion Recognition (SER) is significantly dependent on the quality of emotional speech corpora used for model training. Researchers in the field of SER have developed various corpora by adjusting design parameters to enhance the reliability of the training source. For this study, we focus on exploring communication modes of collection, specifically analyzing spontaneous emotional speech patterns gathered during conversation or monologue. While conversations are acknowledged as effective for eliciting authentic emotional expressions, systematic analyses are necessary to confirm their reliability as a better source of emotional speech data. We investigate this research question from perceptual differences and acoustic variability present in both emotional speeches. Our analyses on multi-lingual corpora show that, first, raters exhibit higher consistency for conversation recordings when evaluating categorical emotions, and second, perceptions and acoustic patterns observed in conversational samples align more closely with expected trends discussed in relevant emotion literature. We further examine the impact of these differences on SER modeling, which shows that we can train a more robust and stable SER model by using conversation data. This work provides comprehensive evidence suggesting that conversation may offer a better source compared to monologue for developing an SER model. 

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. 

When selecting test data for subjective tasks, most studies define ground truth labels using aggregation methods such as the majority or plurality rules. These methods discard data points without consensus, making the test set easier than practical tasks where a prediction is needed for each sample. However, the discarded data points often express ambiguous cues that elicit coexisting traits perceived by annotators. This paper addresses the importance of considering all the annotations and samples in the data, highlighting that only showing the model’s performance on an incomplete test set selected by using the majority or plurality rules can lead to bias in the models’ performances. We focus on speech-emotion recognition (SER) tasks. We observe that traditional aggregation rules have a data loss ratio ranging from 5.63% to 89.17%. From this observation, we propose a flexible method named the all-inclusive aggregation rule to evaluate SER systems on the complete test data. We contrast traditional single-label formulations with a multi-label formulation to consider the coexistence of emotions. We show that training an SER model with the data selected by the all-inclusive aggregation rule shows consistently higher macro-F1 scores when tested in the entire test set, including ambiguous samples without agreement. 

Emotional annotation of data is important in affective computing for the analysis, recognition, and synthesis of emotions. As raters perceive emotion, they make relative comparisons with what they previously experienced, creating “anchors” that influence the annotations. This unconscious influence of the emotional content of previous stimuli in the perception of emotions is referred to as the affective priming effect. This phenomenon is also expected in annotations conducted with out-of-order segments, a common approach for annotating emotional databases. Can the affective priming effect introduce bias in the labels? If yes, how does this bias affect emotion recognition systems trained with these labels? This study presents a detailed analysis of the affective priming effect and its influence on speech emotion recognition (SER). The analysis shows that the affective priming effect affects emotional attributes and categorical emotion annotations. We observe that if annotators assign an extreme score to previous sentences for an emotional attribute (valence, arousal, or dominance), they will tend to annotate the next sentence closer to that extreme. We conduct SER experiments using the most biased sentences. We observe that models trained on the biased sentences perform the best and have the lowest prediction uncertainty.