Audio-language pretraining (ALP) holds promise for learning general-purpose audio representation, yet remains underexplored.Crucially, there is no consensus on whether audio-language models can build effective general-purpose audio encoders, nor a systematic understanding of how pretraining objectives behave across diverse tasks and scales.We identify three key barriers: limited scale of audio-text corpora, limited coverage of audio attributes in existing caption corpora, and lack of systematic exploration and evaluation.To fill this gap, we present the first principled empirical study of ALP.We first introduce Cap-tionStew, a 10.7M caption dataset aggregating open-source audio-text corpora across multiple domains and captioning focuses.We then conduct the first comprehensive evaluation comparing contrastive and captioning objectives for learning audio representation across speech, music, and environmental sound tasks.Our results not only demonstrate that ALP yields competitive, transferable representations, but reveal critical trade-offs: contrastive learning offers superior data efficiency, while captioning exhibits better scalability.Furthermore, we find that the benefits of supervised initialization often diminish at larger scales, challenging common practices.By grounding these claims in empirical evidence, we establish a viable pathway toward general-purpose audio representation learning, guiding future research.

Recent advancements in neural audio codecs have not only enabled superior audio compression but also enhanced speech synthesis techniques. Researchers are now exploring their potential as universal acoustic feature extractors for a broader range of speech processing tasks. Building on this trend, we introduce Codec2Vec, the first speech representation learning framework that relies exclusively on discrete audio codec units. This approach offers several advantages, including improved data storage and transmission efficiency, faster training, and enhanced data privacy. We explore masked prediction with various training target derivation strategies to thoroughly understand the effectiveness of this framework. Evaluated on the SUPERB benchmark, Codec2Vec achieves competitive performance compared to continuous-input models while reducing storage requirements by up to $16.5 \times$ and training time by $2.3 \times$, showcasing its scalability and efficiency.

Workflow scheduling is a well-known NP-complete problem with broad applications and increasing importance. In this paper, we present a heuristic-based algorithm, called FPPTS, which uses a new ranking method in the task ranking phase, prioritizing tasks according to their full paths from the entry task to the exit task. Experimental results show that FPPTS excels at workflows of high CCR running in heterogeneous computing environments, significantly outperforming HEFT and IPPTS. For example, in experiments with 30-task and 10-CCR workflows running on 10 processors, FPPTS shows an average performance improvement of 15.93% compared to IPPTS. The excellent performance of FPPTS indicates a promising direction for future workflow scheduling research.

Multimodal foundation models, such as Gemini and ChatGPT, have revolutionized human-machine interactions by seamlessly integrating various forms of data. Developing a universal spoken language model that comprehends a wide range of natural language instructions is critical for bridging communication gaps and facilitating more intuitive interactions. However, the absence of a comprehensive evaluation benchmark poses a significant challenge. We present Dynamic-SUPERB Phase-2, an open and evolving benchmark for the comprehensive evaluation of instruction-based universal speech models. Building upon the first generation, this second version incorporates 125 new tasks contributed collaboratively by the global research community, expanding the benchmark to a total of 180 tasks, making it the largest benchmark for speech and audio evaluation. While the first generation of Dynamic-SUPERB was limited to classification tasks, Dynamic-SUPERB Phase-2 broadens its evaluation capabilities by introducing a wide array of novel and diverse tasks, including regression and sequence generation, across speech, music, and environmental audio. Evaluation results show that no model performed well universally. SALMONN-13B excelled in English ASR and Qwen2-Audio-7B-Instruct showed high accuracy in emotion recognition, but current models still require further innovations to handle a broader range of tasks. We open-source all task data and the evaluation pipeline at https://github.com/dynamic-superb/dynamic-superb.

Recent advancements in learned 3D representations have enabled significant progress in solving complex robotic manipulation tasks, particularly for rigid-body objects. However, manipulating granular materials such as beans, nuts, and rice remains challenging due to the intricate physics of particle interactions, high-dimensional and partially observable state, inability to visually track individual particles in a pile, and the computational demands of accurate dynamics prediction. Current deep latent dynamics models often struggle to generalize in granular material manipulation due to a lack of inductive biases. In this work, we propose a novel approach that learns a visual dynamics model over Gaussian splatting repre-sentations of scenes and leverages this model for manipulating granular media via Model-Predictive Control. Our method enables efficient optimization for complex manipulation tasks on piles of granular media. We evaluate our approach in both simulated and real-world settings, demonstrating its ability to solve unseen planning tasks and generalize to new environments in a zero-shot transfer. We also show significant prediction and manipulation performance improvements compared to existing granular media manipulation methods.

We introduce RealSync, a novel dataset designed to significantly enhance the training and evaluation of models for audio-visual synchronization (AV Sync) tasks. Sourced from high-quality YouTube channels, RealSync covers a wide range of content domains, providing an improved scale, diversity, and alignment with broadcast content compared to existing datasets. It features extended-length video samples, catering to the critical need for more comprehensive, real-world training and evaluation materials. Alongside this dataset, we present StreamSync, a model tailored for real-world AV Sync applications. StreamSync is designed to be backbone agnostic and incorporates a streaming mechanism that processes consecutive video segments dynamically, iteratively refining synchronization predictions. This innovative approach enables StreamSync to outperform existing models, offering superior synchronization accuracy with minimal computational cost per iteration. Together, our dataset and the StreamSync model establish a new benchmark for AVSync research, promising to drive the development of more robust and practical AVSync methods. https://github.com/jvoas655/StreamSync

This work proposes an arrhythmia classification system. The algorithm includes naive electrocardiography (ECG) data preprocessing procedures that apply to various ECG databases. Additionally, the paper presents an ultra-lightweight model designed for arrhythmia classification, which combines a Convolutional Neural Network (CNN) with long-term heart rate information to enhance the performance of the model. The proposed model was trained and tested using the MIT-BIH and NCKU-CBIC database, following the classification standards of the Association for the Advancement of Medical Instrumentation (AAMI), achieving an accuracy of 98.5% and 97.1%. Furthermore, this work proposes a customized artificial intelligence (AI) accelerator for hardware implementation, which leverages a parallelized processing element (PE) array architecture and hybrid stationary techniques to achieve high-performance computing. The chip implementation achieves a power consumption of 122 μW, a classification latency of 6.8 ms, and an energy efficiency of 0.83 μJ/classification.

Audio-visual pre-trained models have gained substantial attention recently and demonstrated superior performance on various audio-visual tasks. This study investigates whether pre-trained audio-visual models demonstrate non-arbitrary associations between sounds and visual representations-known as sound symbolism-which is also observed in humans. We developed a specialized dataset with synthesized images and audio samples and assessed these models using a non-parametric approach in a zero-shot setting. Our findings reveal a significant correlation between the models’ outputs and established patterns of sound symbolism, particularly in models trained on speech data. These results suggest that such models can capture sound-meaning connections akin to human language processing, providing insights into both cognitive architectures and machine learning strategies.

Prompting has become a practical method for utilizing pre-trained language models (LMs). This approach offers several advantages. It allows an LM to adapt to new tasks with minimal training and parameter updates, thus achieving efficiency in both storage and computation. Additionally, prompting modifies only the LM's inputs and harnesses the generative capabilities of language models to address various downstream tasks in a unified manner. This significantly reduces the need for human labor in designing task-specific models. These advantages become even more evident as the number of tasks served by the LM scales up. Motivated by the strengths of prompting, we are the first to explore the potential of prompting speech LMs in the domain of speech processing. Recently, there has been a growing interest in converting speech into discrete units for language modeling. Our pioneer research demonstrates that these quantized speech units are highly versatile within our unified prompting framework. Not only can they serve as class labels, but they also contain rich phonetic information that can be re-synthesized back into speech signals for speech generation tasks. Specifically, we reformulate speech processing tasks into speech-to-unit generation tasks. As a result, we can seamlessly integrate tasks such as speech classification, sequence generation, and speech generation within a single, unified prompting framework. The experiment results show that the prompting method can achieve competitive performance compared to the strong fine-tuning method based on self-supervised learning models with a similar number of trainable parameters. The prompting method also shows promising results in the few-shot setting. Moreover, with the advanced speech LMs coming into the stage, the proposed prompting framework attains great potential.

The foundation model paradigm leverages a shared foundation model to achieve state-of-the-art (SOTA) performance for various tasks, requiring minimal downstream-specific data collection and modeling. This approach has proven crucial in the field of Natural Language Processing (NLP). However, the speech processing community lacks a similar setup to explore the paradigm systematically. To bridge this gap, we establish the Speech processing Universal PERformance Benchmark (SUPERB). SUPERB represents an ecosystem designed to evaluate foundation models across a wide range of speech processing tasks, facilitating the sharing of results on an online leaderboard and fostering collaboration through a community-driven benchmark database that aids in new development cycles. We present a unified learning framework for solving the speech processing tasks in SUPERB with the frozen foundation model followed by task-specialized lightweight prediction heads. Combining our results with community submissions, we verify that the framework is simple yet effective, as the best-performing foundation model shows competitive generalizability across most SUPERB tasks. Finally, we conduct a series of analyses to offer an in-depth understanding of SUPERB and speech foundation models, including information flows across tasks inside the models and the statistical significance and robustness of the benchmark.

Distilled self-supervised models have shown competitive performance and efficiency in recent years. However, there is a lack of experience in jointly distilling multiple self-supervised speech models. In our work, we performed Ensemble Knowledge Distillation (EKD) on various self-supervised speech models such as HuBERT, RobustHuBERT, and WavLM. We tried two different aggregation techniques, layerwise-average and layerwise-concatenation, to the representations of different teacher models and found that the former was more effective. On top of that, we proposed a multiple prediction head method for student models to predict different layer outputs of multiple teacher models simultaneously. The experimental results show that our method improves the performance of the distilled models on four downstream speech processing tasks, Phoneme Recognition, Speaker Identification, Emotion Recognition, and Automatic Speech Recognition in the hidden-set track of the SUPERB benchmark.

We propose CLA-NeRF - a Category-Level Articulated Neural Radiance Field that can perform view synthesis, part segmentation, and articulated pose estimation. CLA-NeRF is trained at the object category level using no CAD models and no depth, but a set of RGB images with ground truth camera poses and part segments. During inference, it only takes a few RGB views (i.e., few-shot) of an unseen 3D object instance within the known category to infer the object part segmentation and the neural radiance field. Given an articulated pose as input, CLA-NeRF can perform articulation-aware volume rendering to generate the corresponding RGB image at any camera pose. Moreover, the articulated pose of an object can be estimated via inverse rendering. In our experiments, we evaluate the framework across five categories on both synthetic and real-world data. In all cases, our method shows realistic deformation results and accurate articulated pose estimation. We believe that both few-shot articulated object rendering and articulated pose estimation open doors for robots to perceive and interact with unseen articulated objects.

Speech representations learned from Self-supervised learning (SSL) models can benefit various speech processing tasks. However, utilizing SSL representations usually requires fine-tuning the pre-trained models or designing task-specific downstream models and loss functions, causing much memory usage and human labor. Recently, prompting in Natural Language Processing (NLP) has been found to be an efficient technique to leverage pre-trained language models (LMs). Specifically, prompt tuning optimizes a limited number of task-specific parameters with a fixed pre-trained model; as a result, only a small set of parameters is needed to be stored for each task. Prompt tuning improves computation and memory efficiency by leveraging the pre-trained LM's prediction ability. Nevertheless, such a paradigm is little studied in the speech community. We report in this paper the first exploration of the prompt tuning paradigm for speech processing tasks based on Generative Spoken Language Model (GSLM). Experiment results show that the prompt tuning technique achieves competitive performance in speech classification tasks with fewer trainable parameters than fine-tuning specialized downstream models. We further study the technique in challenging sequence generation tasks. Prompt tuning also demonstrates its potential, while the limitation and possible research directions are discussed in this paper. The source code is available on https://github.com/ga642381/SpeechPrompt.

Recently, adapting the idea of self-supervised learning (SSL) on continuous speech has started gaining attention.SSL models pre-trained on a huge amount of unlabeled audio can generate general-purpose representations that benefit a wide variety of speech processing tasks.Despite their ubiquitous deployment, however, the potential privacy risks of these models have not been well investigated.In this paper, we present the first privacy analysis on several SSL speech models using Membership Inference Attacks (MIA) under black-box access.The experiment results show that these pre-trained models are vulnerable to MIA and prone to membership information leakage with high Area Under the Curve (AUC) in both utterance-level and speaker-level.Furthermore, we also conduct several ablation studies to understand the factors that contribute to the success of MIA.

We introduce an offline multi-agent reinforcement learning ( offline MARL) framework that utilizes previously collected data without additional online data collection. Our method reformulates offline MARL as a sequence modeling problem and thus builds on top of the simplicity and scalability of the Transformer architecture. In the fashion of centralized training and decentralized execution, we propose to first train a teacher policy as if the MARL dataset is generated by a single agent. After the teacher policy has identified and recombined the "good" behavior in the dataset, we create separate student policies and distill not only the teacher policy's features but also its structural relations among different agents' features to student policies. Despite its simplicity, the proposed method outperforms state-of-the-art model-free offline MARL baselines while being more robust to demonstration's quality on several environments.

Humans can master a new task within a few trials by drawing upon skills acquired through prior experience. To mimic this capability, hierarchical models combining primitive policies learned from prior tasks have been proposed. However, these methods fall short comparing to the human's range of transferability. We propose a method, which leverages the hierarchical structure to train the combination function and adapt the set of diverse primitive polices alternatively, to efficiently produce a range of complex behaviors on challenging new tasks. We also design two regularization terms to improve the diversity and utilization rate of the primitives in the pre-training phase. We demonstrate that our method outperforms other recent policy transfer methods by combining and adapting these reusable primitives in tasks with continuous action space. The experiment results further show that our approach provides a broader transferring range. The ablation study also show the regularization terms are critical for long range policy transfer. Finally, we show that our method consistently outperforms other methods when the quality of the primitives varies.

Speech quality assessment has been a critical issue in speech processing for decades. Existing automatic evaluations usually require clean references or parallel ground truth data, which is infeasible when the amount of data soars. Subjective tests, on the other hand, do not need any additional clean or parallel data and correlates better to human perception. However, such a test is expensive and time-consuming because crowd work is necessary. It thus becomes highly desired to develop an automatic evaluation approach that correlates well with human perception while not requiring ground truth data. In this paper, we use self-supervised pre-trained models for MOS prediction. We show their representations can distinguish between clean and noisy audios. Then, we fine-tune these pre-trained models followed by simple linear layers in an end-to-end manner. The experiment results showed that our framework outperforms the two previous state-of-the-art models by a significant improvement on Voice Conversion Challenge 2018 and achieves comparable or superior performance on Voice Conversion Challenge 2016. We also conducted an ablation study to further investigate how each module benefits the task. The experiment results are implemented and reproducible with publicly available toolkits.

Self-supervised learning (SSL) has proven vital for advancing research in natural language processing (NLP) and computer vision (CV).The paradigm pretrains a shared model on large volumes of unlabeled data and achieves state-of-the-art (SOTA) for various tasks with minimal adaptation.However, the speech processing community lacks a similar setup to systematically explore the paradigm.To bridge this gap, we introduce Speech processing Universal PERformance Benchmark (SUPERB).SUPERB is a leaderboard to benchmark the performance of a shared model across a wide range of speech processing tasks with minimal architecture changes and labeled data.Among multiple usages of the shared model, we especially focus on extracting the representation learned from SSL for its preferable re-usability.We present a simple framework to solve SUPERB tasks by learning task-specialized lightweight prediction heads on top of the frozen shared model.Our results demonstrate that the framework is promising as SSL representations show competitive generalizability and accessibility across SUPERB tasks.We release SUPERB as a challenge with a leaderboard 1 and a benchmark toolkit 2 to fuel the research in representation learning and general speech processing.