Advertisement videos (ads) play an integral part in the domain of Internet e-commerce as they amplify the reach of particular products to a broad audience or can serve as a medium to raise awareness about specific issues through concise narrative structures. The narrative structures of advertisements involve several elements like reasoning about the broad content (topic and the underlying message) and examining fine-grained details involving the transition of perceived tone due to the specific sequence of events and interaction among characters. In this work, to facilitate the understanding of advertisements along the three important dimensions of topic categorization, perceived tone transition, and social message detection, we introduce a multimodal multilingual benchmark called MM-AU composed of over 8.4K videos (147 hours) curated from multiple web sources. We explore multiple zero-shot reasoning baselines through the application of large language models on the ads transcripts. Further, we demonstrate that leveraging signals from multiple modalities, including audio, video, and text, in multimodal transformer-based supervised models leads to improved performance compared to unimodal approaches.
Traditional music search engines rely on retrieval methods that match natural language queries with music metadata. There have been increasing efforts to expand retrieval methods to consider the audio characteristics of music itself, using queries of various modalities including text, video, and speech. Most approaches aim to match general music semantics to the input queries, while only a few focus on affective qualities. We address the task of retrieving emotionally-relevant music from image queries by proposing a framework for learning an affective alignment between images and music audio. Our approach focuses on learning an emotion-aligned joint embedding space between images and music. This joint embedding space is learned via emotion-supervised contrastive learning, using an adapted cross-modal version of the SupCon loss. We directly evaluate the joint embeddings with cross-modal retrieval tasks (image-to-music and music-to-image) based on emotion labels. In addition, we investigate the generalizability of the learned music embeddings with automatic music tagging as a downstream task. Our experiments show that our approach successfully aligns images and music, and that the learned embedding space is effective for cross-modal retrieval applications.
We address the problem of detecting who spoke when in child-inclusive spoken interactions i.e., automatic child-adult speaker classification. Interactions involving children are richly heterogeneous due to developmental differences. The presence of neurodiversity e.g., due to Autism, contributes additional variability. We investigate the impact of additional pre-training with more unlabelled child speech on the child-adult classification performance. We pre-train our model with child-inclusive interactions, following two recent self-supervision algorithms, Wav2vec 2.0 and WavLM, with a contrastive loss objective. We report 9 - 13% relative improvement over the state-of-the-art baseline with regards to classification F1 scores on two clinical interaction datasets involving children with Autism. We also analyze the impact of pre-training under different conditions by evaluating our model on interactions involving different subgroups of children based on various demographic factors.
Continuously-worn wearable sensors enable researchers to collect copious amounts of rich bio-behavioral time series recordings of real-life activities of daily living, offering unprecedented opportunities to infer novel human behavior patterns during daily routines. Existing approaches to routine discovery through bio-behavioral data rely either on pre-defined notions of activities or use additional non-behavioral measurements as contexts, such as GPS location or localization within the home, presenting risks to user privacy. In this work, we propose a novel wearable time-series mining framework, Hawkes point process On Time series clusters for ROutine Discovery (HOT-ROD), for uncovering behavioral routines from completely unlabeled wearable recordings. We utilize a covariance-based method to generate time-series clusters and discover routines via the Hawkes point process learning algorithm. We empirically validate our approach for extracting routine behaviors using a completely unlabeled time-series collected continuously from over 100 individuals both in and outside of the workplace during a period of ten weeks. Furthermore, we demonstrate this approach intuitively captures daily transitional relationships between physical activity states without using prior knowledge. We also show that the learned behavioral patterns can assist in illuminating an individual's personality and affect.
Over the past few years, Federated Learning (FL) has become an emerging machine learning technique to tackle data privacy challenges through collaborative training. In the Federated Learning algorithm, the clients submit a locally trained model, and the server aggregates these parameters until convergence. Despite significant efforts that have been made to FL in fields like computer vision, audio, and natural language processing, the FL applications utilizing multimodal data streams remain largely unexplored. It is known that multimodal learning has broad real-world applications in emotion recognition, healthcare, multimedia, and social media, while user privacy persists as a critical concern. Specifically, there are no existing FL benchmarks targeting multimodal applications or related tasks. In order to facilitate the research in multimodal FL, we introduce FedMultimodal, the first FL benchmark for multimodal learning covering five representative multimodal applications from ten commonly used datasets with a total of eight unique modalities. FedMultimodal offers a systematic FL pipeline, enabling end-to-end modeling framework ranging from data partition and feature extraction to FL benchmark algorithms and model evaluation. Unlike existing FL benchmarks, FedMultimodal provides a standardized approach to assess the robustness of FL against three common data corruptions in real-life multimodal applications: missing modalities, missing labels, and erroneous labels. We hope that FedMultimodal can accelerate numerous future research directions, including designing multimodal FL algorithms toward extreme data heterogeneity, robustness multimodal FL, and efficient multimodal FL. The datasets and benchmark results can be accessed at: https://github.com/usc-sail/fed-multimodal.
Automatic Speech Understanding (ASU) leverages the power of deep learning models for accurate interpretation of human speech, leading to a wide range of speech applications that enrich the human experience. However, training a robust ASU model requires the curation of a large number of speech samples, creating risks for privacy breaches. In this work, we investigate using foundation models to assist privacy-enhancing speech computing. Unlike conventional works focusing primarily on data perturbation or distributed algorithms, our work studies the possibilities of using pre-trained generative models to synthesize speech content as training data with just label guidance. We show that zero-shot learning with training label-guided synthetic speech content remains a challenging task. On the other hand, our results demonstrate that the model trained with synthetic speech samples provides an effective initialization point for low-resource ASU training. This result reveals the potential to enhance privacy by reducing user data collection but using label-guided synthetic speech content.
Many recent studies have focused on fine-tuning pre-trained models for speech emotion recognition (SER), resulting in promising performance compared to traditional methods that rely largely on low-level, knowledge-inspired acoustic features. These pre-trained speech models learn general-purpose speech representations using self-supervised or weakly-supervised learning objectives from large-scale datasets. Despite the significant advances made in SER through the use of pre-trained architecture, fine-tuning these large pre-trained models for different datasets requires saving copies of entire weight parameters, rendering them impractical to deploy in real-world settings. As an alternative, this work explores parameter-efficient fine-tuning (PEFT) approaches for adapting pre-trained speech models for emotion recognition. Specifically, we evaluate the efficacy of adapter tuning, embedding prompt tuning, and LoRa (Low-rank approximation) on four popular SER testbeds. Our results reveal that LoRa achieves the best fine-tuning performance in emotion recognition while enhancing fairness and requiring only a minimal extra amount of weight parameters. Furthermore, our findings offer novel insights into future research directions in SER, distinct from existing approaches focusing on directly fine-tuning the model architecture. Our code is publicly available under: https://github.com/usc-sail/peft-ser.
Speech processing techniques are useful for analyzing speech and language development in children with Autism Spectrum Disorder (ASD), who are often varied and delayed in acquiring these skills. Early identification and intervention are crucial, but traditional assessment methodologies such as caregiver reports are not adequate for the requisite behavioral phenotyping. Natural Language Sample (NLS) analysis has gained attention as a promising complement. Researchers have developed benchmarks for spoken language capabilities in children with ASD, obtainable through the analysis of NLS. This paper proposes applications of speech processing technologies in support of automated assessment of children's spoken language development by classification between child and adult speech and between speech and nonverbal vocalization in NLS, with respective F1 macro scores of 82.6% and 67.8%, underscoring the potential for accurate and scalable tools for ASD research and clinical use.
Recent studies have explored the use of pre-trained embeddings for speech emotion recognition (SER), achieving comparable performance to conventional methods that rely on low-level knowledge-inspired acoustic features. These embeddings are often generated from models trained on large-scale speech datasets using self-supervised or weakly-supervised learning objectives. Despite the significant advancements made in SER through the use of pre-trained embeddings, there is a limited understanding of the trustworthiness of these methods, including privacy breaches, unfair performance, vulnerability to adversarial attacks, and computational cost, all of which may hinder the real-world deployment of these systems. In response, we introduce TrustSER, a general framework designed to evaluate the trustworthiness of SER systems using deep learning methods, with a focus on privacy, safety, fairness, and sustainability, offering unique insights into future research in the field of SER. Our code is publicly available under: https://github.com/usc-sail/trust-ser.