LLAM
The Lab of Large Audio Model (LLAM) is committed to exploring and advancing the forefront and future of audio and sound technology, and building large audio models.
Recent News
[15/10/2024] $\bullet$ Two research papers from our team have been accepted for presentation at the 26th International Conference on High Performance Computing and Communications (HPCC2024). The accepted papers are titled “Incremental Label Distribution Learning With Scalable Graph Convolutional Networks” and “ESARM: 3D Emotional Speech-To-Animation via Reward Model From Automatically-Ranked Demonstrations.” HPCC2024 is a leading forum for advances in high-performance computing and communications technology. Sponsored by IEEE, the conference brings together experts from academia, industry, and government to address challenges and present innovations in theoretical foundations, systems, infrastructure, tools, and applications. This year’s event continues the conference’s tradition of showcasing cutting-edge research and defining future directions in the rapidly evolving field of high-performance computing. Our team’s participation underscores our commitment to pushing the boundaries of this critical technology.
[20/09/2024] $\bullet$ We are thrilled to announce that our paper, “IDEAW: Robust Neural Audio Watermarking with Invertible Dual-Embedding,” has been officially accepted for presentation at the prestigious EMNLP 2024 main conference! IDEAW represents a significant advancement in neural audio watermarking, and we are excited to share our findings with the NLP community at this premier event.
[16/07/2024] $\bullet$ Today announced the acceptance of its groundbreaking research paper, “Beyond Aggregation: Efficient Federated Model Consolidation with Heterogeneity-Adaptive Weights Diffusion,” at the prestigious Conference on Information and Knowledge Management (CIKM) 2024. This innovative work addresses the critical challenge of communication costs in Federated Learning (FL), a privacy-preserving approach to training machine learning models across decentralized devices. The team pioneers the use of diffusion models, renowned for their success in AI-generated content, to revolutionize how model weights are consolidated on the server-side of FL systems. Our FedDiff method not only significantly reduces communication overhead but also demonstrates remarkable convergence speed, accuracy, and robustness against noise. This research has the potential to unlock broader real-world applications of Federated Learning in fields like healthcare, finance, and IoT. CIKM is an international forum for presenting and discussing cutting-edge research in information and knowledge management. Acceptance at CIKM underscores the significance and quality of this research contribution.
[16/05/2024] $\bullet$ It feels amazing to receive an acceptance notification from a top-tier conference on a weekday afternoon! The latest research paper “Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning,” a collaboration between Ping An Technology’s Dr. Jianzong Wang’s team and Professor Tianyi Zhou’s team from the University of Maryland, has been accepted as a long paper at ACL 2024 CCF Class A paper, with an acceptance rate of less than 20%. This represents a significant breakthrough in the field of instruction-tuning for large models. For the first time, we have revealed the consistency in instruction difficulty perception across models of different scales and achieved over a 20-fold speed improvement in the large model training process through our superfiltering method. This achievement opens up new avenues for data filtering technology. We welcome citations from our peers! Research Highlights: 1. Weak-to-Strong Data Consistency: We discovered that both small and large language models exhibit a high degree of consistency in perceiving and evaluating the difficulty of instruction-tuning data. This finding is crucial for optimizing data filtering processes. 2. Efficient Superfiltering Strategy: We proposed the first superfiltering method that uses small models (e.g., GPT-2) to select data, significantly accelerating the fine-tuning process of large language models. 3. Effectiveness of Selected Training Data: Superfiltering is highly precise in allocating high-quality and information-rich data. Models trained with only 5% of the filtered data performed similarly to or even better than models trained with the entire dataset in multiple benchmark tests. The complete research results and code are publicly available on GitHub: https://github.com/tianyi-lab/Superfiltering. This is our second paper at a top NLP conference. Our team’s collaboration with the University of Maryland has already resulted in a paper published at NAACL, addressing the innovative problem of how to automatically identify high-quality instruction data from datasets during large model training.
[09/05/2024] $\bullet$ The 2024 Twentieth International Conference on Intelligent Computing (ICIC 2024) is scheduled to take place from August 5th to 8th, 2024, in Tianjin, China. In the recently released acceptance notifications, our two latest research endeavors have been selected for oral presentation. They are respectively titled “RREH: Reconstruction Relations Embedded Hashing for Semi-Paired Cross-Modal Retrieval” and “Enhancing Emotion Prediction and Recognition in Conversation through Fine-Grained Emotional Cue Analysis and Cross-Modal Fusion”. We eagerly anticipate sharing the content of our research achievements with the Intelligent Computing community at ICIC2024.
Research Direction
Large Audio Model
Research on Large Audio Models aims to advance the field of audio processing, generation, understanding, and multimodal processing, with the goal of enabling new and innovative applications in areas such as speech recognition, virtual assistants, music composition, audio synthesis, and more.
Text to Speech
Research on high-quality audio, few-shot TTS, low resource TTS, and expressive TTS is mainly applied to scenarios such as speech interaction, information broadcasting, and text-to-speech reading, as well as in intelligent voice outbound calls and intelligent agents.
Voice Conversion
Research that aims to transform the vocal characteristics of a speaker while preserving the linguistic content of their speech. It has various applications in speech processing, including speaker adaptation, voice disguise, and emotion transfer.
Speech Security
Research aims to address various security threats and vulnerabilities associated with speech data, speech recognition systems, and voice communication.
Music AI
Research topics related to music information retrieval, including song detection, singer identification, main melody extraction, and voice beautification.
Latest Publication
The audio watermarking technique embeds messages into audio and accurately extracts messages from the watermarked audio. Traditional methods develop algorithms based on expert experience to embed watermarks into the time-domain or transform-domain of signals. With the development of deep neural networks, deep learning-based neural audio watermarking has emerged. Compared to traditional algorithms, neural audio watermarking achieves better robustness by considering various attacks during training. However, current neural watermarking methods suffer from low capacity and unsatisfactory imperceptibility. Additionally, the issue of watermark locating, which is extremely important and even more pronounced in neural audio watermarking, has not been adequately studied. In this paper, we design a dual-embedding watermarking model for efficient locating. We also consider the impact of the attack layer on the invertible neural network in robustness training, improving the model to enhance both its reasonableness and stability. Experiments show that the proposed model, IDEAW, can withstand various attacks with higher capacity and more efficient locating ability compared to existing methods. The code is available at https://largeaudiomodel.com/IDEAW.
