Generic pre-trained speech and text representations promise to reduce the need for large labeled datasets on specific speech and language tasks. However, it is not clear how to effectively adapt these representations for speech emotion recognition. Recent public benchmarks show the efficacy of several popular self-supervised speech representations for emotion classification. In this study, we show that the primary difference between the top-performing representations is in predicting valence while the differences in predicting activation and dominance dimensions are less pronounced. However, we show that even the best-performing HuBERT representation underperforms on valence prediction compared to a multimodal model that also incorporates text representation. We address this shortcoming by injecting lexical information into the speech representation using the multimodal model as a teacher. To improve the efficacy of our approach, we propose a novel estimate of the quality of the emotion predictions, to condition teacher-student training. We report new audio-only state-of-the-art concordance correlation coefficient (CCC) values of 0.757, 0.627, 0.671 for activation, valence and dominance predictions, respectively, on the MSP-Podcast corpus, and also state-of-the-art values of 0.667, 0.582, 0.545 on the IEMOCAP corpus.
Analysing expressions on the person's face plays a very vital role in identifying emotions and behavior of a person. Recognizing these expressions automatically results in a crucial component of natural human-machine interfaces. Therefore research in this field has a wide range of applications in bio-metric authentication, surveillance systems , emotion to emoticons in various social media platforms. Another application includes conducting customer satisfaction surveys. As we know that the large corporations made huge investments to get feedback and do surveys but fail to get equitable responses. Emotion & Gender recognition through facial gestures is a technology that aims to improve product and services performance by monitoring customer behavior to specific products or service staff by their evaluation. In the past few years there have been a wide variety of advances performed in terms of feature extraction mechanisms , detection of face and also expression classification techniques. This paper is the implementation of an Ensemble CNN for building a real-time system that can detect emotion and gender of the person. The experimental results shows accuracy of 68% for Emotion classification into 7 classes (angry, fear , sad , happy , surprise , neutral , disgust) on FER-2013 dataset and 95% for Gender classification (Male or Female) on IMDB dataset. Our work can predict emotion and gender on single face images as well as multiple face images. Also when input is given through webcam our complete pipeline of this real-time system can take less than 0.5 seconds to generate results.
Multimodal emotion recognition study is hindered by the lack of labelled corpora in terms of scale and diversity, due to the high annotation cost and label ambiguity. In this paper, we propose a pre-training model \textbf{MEmoBERT} for multimodal emotion recognition, which learns multimodal joint representations through self-supervised learning from large-scale unlabeled video data that come in sheer volume. Furthermore, unlike the conventional "pre-train, finetune" paradigm, we propose a prompt-based method that reformulates the downstream emotion classification task as a masked text prediction one, bringing the downstream task closer to the pre-training. Extensive experiments on two benchmark datasets, IEMOCAP and MSP-IMPROV, show that our proposed MEmoBERT significantly enhances emotion recognition performance.
Self-supervised learning methods such as wav2vec 2.0 have shown promising results in learning speech representations from unlabelled and untranscribed speech data that are useful for speech recognition. Since these representations are learned without any task-specific supervision, they can also be useful for other voice-activated tasks like speaker verification, keyword spotting, emotion classification etc. In our work, we propose a general purpose framework for adapting a pre-trained wav2vec 2.0 model for different voice-activated tasks. We develop downstream network architectures that operate on the contextualized speech representations of wav2vec 2.0 to adapt the representations for solving a given task. Finally, we extend our framework to perform multi-task learning by jointly optimizing the network parameters on multiple voice activated tasks using a shared transformer backbone. Both of our single and multi-task frameworks achieve state-of-the-art results in speaker verification and keyword spotting benchmarks. Our best performing models achieve 1.98% and 3.15% EER on VoxCeleb1 test set when trained on VoxCeleb2 and VoxCeleb1 respectively, and 98.23% accuracy on Google Speech Commands v1.0 keyword spotting dataset.
EEG signals have been reported to be informative and reliable for emotion recognition in recent years. However, the inter-subject variability of emotion-related EEG signals still poses a great challenge for the practical applications of EEG-based emotion recognition. Inspired by recent neuroscience studies on inter-subject correlation, we proposed a Contrastive Learning method for Inter-Subject Alignment (CLISA) to tackle the cross-subject emotion recognition problem. Contrastive learning was employed to minimize the inter-subject differences by maximizing the similarity in EEG signal representations across subjects when they received the same emotional stimuli in contrast to different ones. Specifically, a convolutional neural network was applied to learn inter-subject aligned spatiotemporal representations from EEG time series in contrastive learning. The aligned representations were subsequently used to extract differential entropy features for emotion classification. CLISA achieved state-of-the-art cross-subject emotion recognition performance on our THU-EP dataset with 80 subjects and the publicly available SEED dataset with 15 subjects. It could generalize to unseen subjects or unseen emotional stimuli in testing. Furthermore, the spatiotemporal representations learned by CLISA could provide insights into the neural mechanisms of human emotion processing.
Several recent studies on dyadic human-human interactions have been done on conversations without specific business objectives. However, many companies might benefit from studies dedicated to more precise environments such as after sales services or customer satisfaction surveys. In this work, we place ourselves in the scope of a live chat customer service in which we want to detect emotions and their evolution in the conversation flow. This context leads to multiple challenges that range from exploiting restricted, small and mostly unlabeled datasets to finding and adapting methods for such context.We tackle these challenges by using Few-Shot Learning while making the hypothesis it can serve conversational emotion classification for different languages and sparse labels. We contribute by proposing a variation of Prototypical Networks for sequence labeling in conversation that we name ProtoSeq. We test this method on two datasets with different languages: daily conversations in English and customer service chat conversations in French. When applied to emotion classification in conversations, our method proved to be competitive even when compared to other ones.
Automatic emotion recognition (AER) based on enriched multimodal inputs, including text, speech, and visual clues, is crucial in the development of emotionally intelligent machines. Although complex modality relationships have been proven effective for AER, they are still largely underexplored because previous works predominantly relied on various fusion mechanisms with simply concatenated features to learn multimodal representations for emotion classification. This paper proposes a novel hierarchical fusion graph convolutional network (HFGCN) model that learns more informative multimodal representations by considering the modality dependencies during the feature fusion procedure. Specifically, the proposed model fuses multimodality inputs using a two-stage graph construction approach and encodes the modality dependencies into the conversation representation. We verified the interpretable capabilities of the proposed method by projecting the emotional states to a 2D valence-arousal (VA) subspace. Extensive experiments showed the effectiveness of our proposed model for more accurate AER, which yielded state-of-the-art results on two public datasets, IEMOCAP and MELD.
Fine-grained classification involves dealing with datasets with larger number of classes with subtle differences between them. Guiding the model to focus on differentiating dimensions between these commonly confusable classes is key to improving performance on fine-grained tasks. In this work, we analyse the contrastive fine-tuning of pre-trained language models on two fine-grained text classification tasks, emotion classification and sentiment analysis. We adaptively embed class relationships into a contrastive objective function to help differently weigh the positives and negatives, and in particular, weighting closely confusable negatives more than less similar negative examples. We find that Label-aware Contrastive Loss outperforms previous contrastive methods, in the presence of larger number and/or more confusable classes, and helps models to produce output distributions that are more differentiated.
Identifying emotions from text is crucial for a variety of real world tasks. We consider the two largest now-available corpora for emotion classification: GoEmotions, with 58k messages labelled by readers, and Vent, with 33M writer-labelled messages. We design a benchmark and evaluate several feature spaces and learning algorithms, including two simple yet novel models on top of BERT that outperform previous strong baselines on GoEmotions. Through an experiment with human participants, we also analyze the differences between how writers express emotions and how readers perceive them. Our results suggest that emotions expressed by writers are harder to identify than emotions that readers perceive. We share a public web interface for researchers to explore our models.
Existing audio-language task-specific predictive approaches focus on building complicated late-fusion mechanisms. However, these models are facing challenges of overfitting with limited labels and low model generalization abilities. In this paper, we present a Cross-modal Transformer for Audio-and-Language, i.e., CTAL, which aims to learn the intra-modality and inter-modality connections between audio and language through two proxy tasks on a large amount of audio-and-language pairs: masked language modeling and masked cross-modal acoustic modeling. After fine-tuning our pre-trained model on multiple downstream audio-and-language tasks, we observe significant improvements across various tasks, such as, emotion classification, sentiment analysis, and speaker verification. On this basis, we further propose a specially-designed fusion mechanism that can be used in fine-tuning phase, which allows our pre-trained model to achieve better performance. Lastly, we demonstrate detailed ablation studies to prove that both our novel cross-modality fusion component and audio-language pre-training methods significantly contribute to the promising results.
Automatic speech emotion recognition (SER) is a challenging task that plays a crucial role in natural human-computer interaction. One of the main challenges in SER is data scarcity, i.e., insufficient amounts of carefully labeled data to build and fully explore complex deep learning models for emotion classification. This paper aims to address this challenge using a transfer learning strategy combined with spectrogram augmentation. Specifically, we propose a transfer learning approach that leverages a pre-trained residual network (ResNet) model including a statistics pooling layer from speaker recognition trained using large amounts of speaker-labeled data. The statistics pooling layer enables the model to efficiently process variable-length input, thereby eliminating the need for sequence truncation which is commonly used in SER systems. In addition, we adopt a spectrogram augmentation technique to generate additional training data samples by applying random time-frequency masks to log-mel spectrograms to mitigate overfitting and improve the generalization of emotion recognition models. We evaluate the effectiveness of our proposed approach on the interactive emotional dyadic motion capture (IEMOCAP) dataset. Experimental results indicate that the transfer learning and spectrogram augmentation approaches improve the SER performance, and when combined achieve state-of-the-art results.
Classification of human emotions can play an essential role in the design and improvement of human-machine systems. While individual biological signals such as Electrocardiogram (ECG) and Electrodermal Activity (EDA) have been widely used for emotion recognition with machine learning methods, multimodal approaches generally fuse extracted features or final classification/regression results to boost performance. To enhance multimodal learning, we present a novel attentive cross-modal connection to share information between convolutional neural networks responsible for learning individual modalities. Specifically, these connections improve emotion classification by sharing intermediate representations among EDA and ECG and apply attention weights to the shared information, thus learning more effective multimodal embeddings. We perform experiments on the WESAD dataset to identify the best configuration of the proposed method for emotion classification. Our experiments show that the proposed approach is capable of learning strong multimodal representations and outperforms a number of baselines methods.
Emotion classification in text is typically performed with neural network models which learn to associate linguistic units with emotions. While this often leads to good predictive performance, it does only help to a limited degree to understand how emotions are communicated in various domains. The emotion component process model (CPM) by Scherer (2005) is an interesting approach to explain emotion communication. It states that emotions are a coordinated process of various subcomponents, in reaction to an event, namely the subjective feeling, the cognitive appraisal, the expression, a physiological bodily reaction, and a motivational action tendency. We hypothesize that these components are associated with linguistic realizations: an emotion can be expressed by describing a physiological bodily reaction ("he was trembling"), or the expression ("she smiled"), etc. We annotate existing literature and Twitter emotion corpora with emotion component classes and find that emotions on Twitter are predominantly expressed by event descriptions or subjective reports of the feeling, while in literature, authors prefer to describe what characters do, and leave the interpretation to the reader. We further include the CPM in a multitask learning model and find that this supports the emotion categorization. The annotated corpora are available at https://www.ims.uni-stuttgart.de/data/emotion.
This article presents a benchmark study of symbolic piano music classification using the masked language modelling approach of the Bidirectional Encoder Representations from Transformers (BERT). Specifically, we consider two types of MIDI data: MIDI scores, which are musical scores rendered directly into MIDI with no dynamics and precisely aligned with the metrical grid notated by its composer and MIDI performances, which are MIDI encodings of human performances of musical scoresheets. With five public-domain datasets of single-track piano MIDI files, we pre-train two 12-layer Transformer models using the BERT approach, one for MIDI scores and the other for MIDI performances, and fine-tune them for four downstream classification tasks. These include two note-level classification tasks (melody extraction and velocity prediction) and two sequence-level classification tasks (style classification and emotion classification). Our evaluation shows that the BERT approach leads to higher classification accuracy than recurrent neural network (RNN)-based baselines.
In this report, address the problem of sentiment classification on the Twitter dataset. used a number of machine learning and deep learning methods to perform sentiment analysis. In the end, used a majority vote ensemble method with 5 of our best models to achieve the classification accuracy of 83.58% on Kaggle public leaderboard.
Detecting what emotions are expressed in text is a well-studied problem in natural language processing. However, research on finer grained emotion analysis such as what causes an emotion is still in its infancy. We present solutions that tackle both emotion recognition and emotion cause detection in a joint fashion. Considering that common-sense knowledge plays an important role in understanding implicitly expressed emotions and the reasons for those emotions, we propose novel methods that combine common-sense knowledge via adapted knowledge models with multi-task learning to perform joint emotion classification and emotion cause tagging. We show performance improvement on both tasks when including common-sense reasoning and a multitask framework. We provide a thorough analysis to gain insights into model performance.
Recently, there has been an increasing interest in neural speech synthesis. While the deep neural network achieves the state-of-the-art result in text-to-speech (TTS) tasks, how to generate a more emotional and more expressive speech is becoming a new challenge to researchers due to the scarcity of high-quality emotion speech dataset and the lack of advanced emotional TTS model. In this paper, we first briefly introduce and publicly release a Mandarin emotion speech dataset including 9,724 samples with audio files and its emotion human-labeled annotation. After that, we propose a simple but efficient architecture for emotional speech synthesis called EMSpeech. Unlike those models which need additional reference audio as input, our model could predict emotion labels just from the input text and generate more expressive speech conditioned on the emotion embedding. In the experiment phase, we first validate the effectiveness of our dataset by an emotion classification task. Then we train our model on the proposed dataset and conduct a series of subjective evaluations. Finally, by showing a comparable performance in the emotional speech synthesis task, we successfully demonstrate the ability of the proposed model.
Symbolic music understanding, which refers to the understanding of music from the symbolic data (e.g., MIDI format, but not audio), covers many music applications such as genre classification, emotion classification, and music pieces matching. While good music representations are beneficial for these applications, the lack of training data hinders representation learning. Inspired by the success of pre-training models in natural language processing, in this paper, we develop MusicBERT, a large-scale pre-trained model for music understanding. To this end, we construct a large-scale symbolic music corpus that contains more than 1 million music songs. Since symbolic music contains more structural (e.g., bar, position) and diverse information (e.g., tempo, instrument, and pitch), simply adopting the pre-training techniques from NLP to symbolic music only brings marginal gains. Therefore, we design several mechanisms, including OctupleMIDI encoding and bar-level masking strategy, to enhance pre-training with symbolic music data. Experiments demonstrate the advantages of MusicBERT on four music understanding tasks, including melody completion, accompaniment suggestion, genre classification, and style classification. Ablation studies also verify the effectiveness of our designs of OctupleMIDI encoding and bar-level masking strategy in MusicBERT.
Emotion recognition from speech is a challenging task. Re-cent advances in deep learning have led bi-directional recur-rent neural network (Bi-RNN) and attention mechanism as astandard method for speech emotion recognition, extractingand attending multi-modal features - audio and text, and thenfusing them for downstream emotion classification tasks. Inthis paper, we propose a simple yet efficient neural networkarchitecture to exploit both acoustic and lexical informationfrom speech. The proposed framework using multi-scale con-volutional layers (MSCNN) to obtain both audio and text hid-den representations. Then, a statistical pooling unit (SPU)is used to further extract the features in each modality. Be-sides, an attention module can be built on top of the MSCNN-SPU (audio) and MSCNN (text) to further improve the perfor-mance. Extensive experiments show that the proposed modeloutperforms previous state-of-the-art methods on IEMOCAPdataset with four emotion categories (i.e., angry, happy, sadand neutral) in both weighted accuracy (WA) and unweightedaccuracy (UA), with an improvement of 5.0% and 5.2% respectively under the ASR setting.
The task of classifying emotions within a musical track has received widespread attention within the Music Information Retrieval (MIR) community. Music emotion recognition has traditionally relied on the use of acoustic features, verbal features, and metadata-based filtering. The role of musical prosody remains under-explored despite several studies demonstrating a strong connection between prosody and emotion. In this study, we restrict the input of traditional machine learning algorithms to the features of musical prosody. Furthermore, our proposed approach builds upon the prior by classifying emotions under an expanded emotional taxonomy, using the Geneva Wheel of Emotion. We utilize a methodology for individual data collection from vocalists, and personal ground truth labeling by the artist themselves. We found that traditional machine learning algorithms when limited to the features of musical prosody (1) achieve high accuracies for a single singer, (2) maintain high accuracy when the dataset is expanded to multiple singers, and (3) achieve high accuracies when trained on a reduced subset of the total features.