A universal audio representation should capture fine-grained speech cues and high-level semantics for environmental sounds and music in a single encoder. Existing encoders often excel in one domain but degrade in others. We propose UniWhisper, an efficient continual multi-task training framework that casts heterogeneous audio tasks into a unified instruction and answer format. This enables standard next-token training without task-specific heads and losses. We train it on 38k hours of public audio and assess the encoder using shallow MLP probes and k-nearest neighbors (kNN) on 20 tasks spanning speech, environmental sound, and music. UniWhisper reaches normalized weighted averages of 0.81 with MLP probes and 0.61 with kNN, compared to 0.64 and 0.46 for Whisper, while retaining strong speech performance.
What to Remember: Self-Adaptive Continual Learning for Audio Deepfake Detection
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所多模态人工智能系统国家重点实验室）；School of Computer and Information Technology, University of Beijing Jiaotong（北京交通大学计算机与信息技术学院）；Department of Automation, Tsinghua University（清华大学自动化系）；University of Science and Technology of China（中国科学技术大学）
Automated audio captioning (AAC) is the task of automatically creating textual descriptions (i.e. captions) for the contents of a general audio signal. Most AAC methods are using existing datasets to optimize and/or evaluate upon. Given the limited information held by the AAC datasets, it is very likely that AAC methods learn only the information contained in the utilized datasets. In this paper we present a first approach for continuously adapting an AAC method to new information, using a continual learning method. In our scenario, a pre-optimized AAC method is used for some unseen general au…
Characterizing Continual Learning Scenarios and Strategies for Audio Analysis
Indian Institute of Technology Ropar（印度理工学院罗帕尔分校）；University of Regensburg（雷根斯堡大学）；Inception Institute of AI（Inception人工智能研究院）；Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI)（穆罕默德·本·扎耶德人工智能大学）；University of Ottawa（渥太华大学）
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）
Fake audio attack becomes a major threat to the speaker verification system. Although current detection approaches have achieved promising results on dataset-specific scenarios, they encounter difficulties on unseen spoofing data. Fine-tuning and retraining from scratch have been applied to incorporate new data. However, fine-tuning leads to performance degradation on previous data. Retraining takes a lot of time and computation resources. Besides, previous data are unavailable due to privacy in some situations. To solve the above problems, this paper proposes detecting fake without forgetting…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Mila--Quebec Artificial Intelligence Institute（米拉-魁北克人工智能研究所）；Adobe Research（奥多比研究院）
Continual learning consists in incrementally training a model on a sequence of datasets and testing on the union of all datasets. In this paper, we examine continual learning for the problem of sound classification, in which we wish to refine already trained models to learn new sound classes. In practice one does not want to maintain all past training data and retrain from scratch, but naively updating a model with new data(sets) results in a degradation of already learned tasks, which is referred to as "catastrophic forgetting." We develop a generative replay procedure for generating training…
SLAM-LLM: A Modular, Open-Source Multimodal Large Language Model Framework and Best Practice for Speech, Language, Audio and Music Processing
X-LANCE Lab, School of Computer Science, MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University（X-LANCE实验室，计算机科学学院，人工智能教育部重点实验室，上海交通大学）；Tongyi Lab, Alibaba Group（通义实验室，阿里巴巴集团）；Peng Cheng Laboratory（鹏城实验室）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；Tianjin University（天津大学）；Hong Kong University of Science and Technology（香港科学大学）；Queen Mary University of London（伦敦玛丽女王大学）；Nanyang Technological University（南洋理工大学）；Shanghai Innovation Institute（上海创新研究院）
End-to-end (E2E) automatic speech recognition (ASR) models have recently demonstrated superior performance over the traditional hybrid ASR models. Training an E2E ASR model requires a large amount of data which is not only expensive but may also raise dependency on production data. At the same time, synthetic speech generated by the state-of-the-art text-to-speech (TTS) engines has advanced to near-human naturalness. In this work, we propose to utilize synthetic speech for ASR training (SynthASR) in applications where data is sparse or hard to get for ASR model training. In addition, we apply …
