Publications (18)
End-to-end Listen, Look, Speak and Act
Siyin Wang, Wenyi Yu, Xianzhao Chen +4
Human interaction is inherently multimodal and full-duplex: we listen while watching, speak while acting, and fluidly adapt to turn-taking and interruptions. Realizing these capabi…
Adaptive Conditional Expert Selection Network for Multi-domain Recommendation
Kuiyao Dong, Xingyu Lou, Feng Liu +4
Mixture-of-Experts (MOE) has recently become the de facto standard in Multi-domain recommendation (MDR) due to its powerful expressive ability. However, such MOE-based method typic…
MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence
Sonal Kumar, Å imon SedláÄek, Vaibhavi Lokegaonkar +31
Audio comprehension-including speech, non-speech sounds, and music-is essential for achieving human-level intelligence. Consequently, AI agents must demonstrate holistic audio unde…
Enabling Auditory Large Language Models for Automatic Speech Quality Evaluation
Siyin Wang, Wenyi Yu, Yudong Yang +10
Speech quality assessment typically requires evaluating audio from multiple aspects, such as mean opinion score (MOS) and speaker similarity (SIM) \etc., which can be challenging t…
video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models
Guangzhi Sun, Wenyi Yu, Changli Tang +7
Speech understanding as an element of the more generic video understanding using audio-visual large language models (av-LLMs) is a crucial yet understudied aspect. This paper propo…
SALMONN-omni: A Codec-free LLM for Full-duplex Speech Understanding and Generation
Wenyi Yu, Siyin Wang, Xiaoyu Yang +7
Full-duplex multimodal large language models (LLMs) provide a unified framework for addressing diverse speech understanding and generation tasks, enabling more natural and seamless…
SALMONN-2: Advancing General-Purpose Hearing Abilities with Self-Supervised Representations
Xiaoyu Yang, Xuenan Xu, Wenyi Yu +10
Recent audio large language models (ALLMs) are typically built upon audio encoders trained with large amounts of supervised data. Since self-supervised learning (SSL) audio encoder…
Can Large Language Models Understand Spatial Audio?
Changli Tang, Wenyi Yu, Guangzhi Sun +8
This paper explores enabling large language models (LLMs) to understand spatial information from multichannel audio, a skill currently lacking in auditory LLMs. By leveraging LLMs'…
Connecting Speech Encoder and Large Language Model for ASR
Wenyi Yu, Changli Tang, Guangzhi Sun +6
The impressive capability and versatility of large language models (LLMs) have aroused increasing attention in automatic speech recognition (ASR), with several pioneering studies a…
Extract and Diffuse: Latent Integration for Improved Diffusion-based Speech and Vocal Enhancement
Yudong Yang, Zhan Liu, Wenyi Yu +3
Diffusion-based generative models have recently achieved remarkable results in speech and vocal enhancement due to their ability to model complex speech data distributions. While t…
QualiSpeech: A Speech Quality Assessment Dataset with Natural Language Reasoning and Descriptions
Siyin Wang, Wenyi Yu, Xianzhao Chen +7
This paper explores a novel perspective to speech quality assessment by leveraging natural language descriptions, offering richer, more nuanced insights than traditional numerical…
Fine-grained Audio-Visual Joint Representations for Multimodal Large Language Models
Guangzhi Sun, Wenyi Yu, Changli Tang +6
Audio-visual large language models (LLM) have drawn significant attention, yet the fine-grained combination of both input streams is rather under-explored, which is challenging but…
MAV: A Multimodal, Multigenre, and Multipurpose Audio-Visual Academic Lecture Dataset
Zhe Chen, Heyang Liu, Wenyi Yu +6
Publishing open-source academic video recordings is an emergent and prevalent approach to sharing knowledge online. Such videos carry rich multimodal information including speech,…
HMDN: Hierarchical Multi-Distribution Network for Click-Through Rate Prediction
Xingyu Lou, Yu Yang, Kuiyao Dong +5
As the recommendation service needs to address increasingly diverse distributions, such as multi-population, multi-scenario, multitarget, and multi-interest, more and more recent w…
An Improved Empirical Fisher Approximation for Natural Gradient Descent
Xiaodong Wu, Wenyi Yu, Chao Zhang +1
Approximate Natural Gradient Descent (NGD) methods are an important family of optimisers for deep learning models, which use approximate Fisher information matrices to pre-conditio…
SALMONN-omni: A Standalone Speech LLM without Codec Injection for Full-duplex Conversation
Wenyi Yu, Siyin Wang, Xiaoyu Yang +7
In order to enable fluid and natural human-machine speech interaction, existing full-duplex conversational systems often adopt modular architectures with auxiliary components such…
SALMONN: Towards Generic Hearing Abilities for Large Language Models
Changli Tang, Wenyi Yu, Guangzhi Sun +6
Hearing is arguably an essential ability of artificial intelligence (AI) agents in the physical world, which refers to the perception and understanding of general auditory informat…
Towards General Auditory Intelligence: Large Multimodal Models for Machine Listening and Speaking
Siyin Wang, Zengrui Jin, Changli Tang +26
In the era of large language models (LLMs) and artificial general intelligence (AGI), computer audition must evolve beyond traditional paradigms to fully leverage the capabilities…