This paper presents Step-Audio 2, an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation. By integrating a latent audio encoder and reasoning-centric reinforcement learning (RL), Step-Audio 2 achieves promising performance in automatic speech recognition (ASR) and audio understanding. To facilitate genuine end-to-end speech conversation, Step-Audio 2 incorporates the generation of discrete audio tokens into language modeling, significantly enhancing its responsiveness to paralinguistic information such as speaking styles and emotions. To effectively leverage the rich textual and acoustic knowledge in real-world data, Step-Audio 2 integrates retrieval-augmented generation (RAG) and is able to call external tools such as web search to mitigate hallucination and audio search to switch timbres. Trained on millions of hours of speech and audio data, Step-Audio 2 delivers intelligence and expressiveness across diverse conversational scenarios. Evaluation results demonstrate that Step-Audio 2 achieves state-of-the-art performance on various audio understanding and conversational benchmarks compared to other open-source and commercial solutions. Please visit https://github.com/stepfun-ai/Step-Audio2 for more information.
University of Jyväskylä（于韦斯屈莱大学）；Workspace Oy（Workspace公司）
Sociometric badges are an emerging technology for study how teams interact in physical places. Audio data recorded by sociometric badges is often downsampled to not record discussions of the sociometric badges holders. To gain more information about interactions inside teams with sociometric badges a Voice Activity Detector (VAD) is deployed to measure verbal activity of the interaction. Detecting voice activity from downsampled audio data is challenging because down-sampling destroys information from the data. We developed a VAD using deep learning techniques that achieves only moderate accur…
Within the audio research community and the industry, keyword spotting (KWS) and audio tagging (AT) are seen as two distinct tasks and research fields. However, from a technical point of view, both of these tasks are identical: they predict a label (keyword in KWS, sound event in AT) for some fixed-sized input audio segment. This work proposes UniKW-AT: An initial approach for jointly training both KWS and AT. UniKW-AT enhances the noise-robustness for KWS, while also being able to predict specific sound events and enabling conditional wake-ups on sound events. Our approach extends the AT pipe…
In this paper, we evaluate deep learning-enabled AED systems against evasion attacks based on adversarial examples. We test the robustness of multiple security critical AED tasks, implemented as CNNs classifiers, as well as existing third-party Nest devices, manufactured by Google, which run their own black-box deep learning models. Our adversarial examples use audio perturbations made of white and background noises. Such disturbances are easy to create, to perform and to reproduce, and can be accessible to a large number of potential attackers, even non-technically savvy ones. We show that an…
This article has been withdrawn by arXiv administrators because the submitter did not have the legal authority to grant the license applied to the work.
Stanford University（斯坦福大学）；McGill University（麦吉尔大学）；École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）；University of California, San Diego（加利福尼亚大学圣地亚哥分校）
The following technical report presents a formal approach to probabilistic minimalist grammar parameter estimation. We describe a formalization of a minimalist grammar. We then present an algorithm for the application of variational Bayesian inference to this formalization.
Conversational Question Answering is a challenging task since it requires understanding of conversational history. In this project, we propose a new system RoBERTa + AT +KD, which involves rationale tagging multi-task, adversarial training, knowledge distillation and a linguistic post-process strategy. Our single model achieves 90.4(F1) on the CoQA test set without data augmentation, outperforming the current state-of-the-art single model by 2.6% F1.
This technical report presents a text-to-image neural network "Emojich" that generates emojis using captions in Russian language as a condition. We aim to keep the generalization ability of a pretrained big model ruDALL-E Malevich (XL) 1.3B parameters at the fine-tuning stage, while giving special style to the images generated. Here are presented some engineering methods, code realization, all hyper-parameters for reproducing results and a Telegram bot where everyone can create their own customized sets of stickers. Also, some newly generated emojis obtained by "Emojich" model are demonstrated…
Mainz University Of Applied Sciences（美因茨应用科学大学）；Universität Stuttgart（斯图加特大学）；Universität Koblenz（科布伦茨大学）；University of Southampton（南安普顿大学）
We introduce an approach to semantically represent and query raster data in a Semantic Web graph. We extend the GeoSPARQL vocabulary and query language to support raster data as a new type of geospatial data. We define new filter functions and illustrate our approach using several use cases on real-world data sets. Finally, we describe a prototypical implementation and validate the feasibility of our approach.
