Related papers: VoxServe: Streaming-Centric Serving System for Spe…

Large Language Models (LLMs) have recently garnered significant attention, primarily for their capabilities in text-based interactions. However, natural human interaction often relies on speech, necessitating a shift towards voice-based…

Multimodal Large Language Models excel at offline audio-visual understanding, but their ability to serve as mobile assistants in continuous real-world streams remains underexplored. In daily phone use, mobile assistants must track streaming…

Recent significant advancements in Large Language Models (LLMs) have greatly propelled the development of Role-Playing Conversational Agents (RPCAs). These systems aim to create immersive user experiences through consistent persona…

Speaker extraction seeks to extract the target speech in a multi-talker scenario given an auxiliary reference. Such reference can be auditory, i.e., a pre-recorded speech, visual, i.e., lip movements, or contextual, i.e., phonetic sequence.…

This work proposes an efficient method to enhance the quality of corrupted speech signals by leveraging both acoustic and visual cues. While existing diffusion-based approaches have demonstrated remarkable quality, their applicability is…

The VoxCeleb Speaker Recognition Challenge (VoxSRC) at Interspeech 2020 offers a challenging evaluation for speaker recognition systems, which includes celebrities playing different parts in movies. The goal of this work is robust speaker…

This paper describes HyperStream, a large-scale, flexible and robust software package, written in the Python language, for processing streaming data with workflow creation capabilities. HyperStream overcomes the limitations of other…

Large language models (LLMs) have shown incredible proficiency in performing tasks that require semantic understanding of natural language instructions. Recently, many works have further expanded this capability to perceive multimodal audio…

Vision-Language Models (VLMs) are increasingly deployed in real-time applications such as autonomous driving and human-computer interaction, which demand fast and reliable responses based on accurate perception. To meet these requirements,…

Large language model (LLM) services are mostly centralized, leading to scalability bottlenecks and underutilization of substantial scattered GPU resources. While decentralization offers a promising alternative, existing frameworks primarily…

The Mixture of Experts (MoE) models are emerging as the latest paradigm for Large Language Models (LLMs). However, due to memory constraints, MoE models with billions or even trillions of parameters can only be deployed in multi-GPU or even…

Attention-based models have been gaining popularity recently for their strong performance demonstrated in fields such as machine translation and automatic speech recognition. One major challenge of attention-based models is the need of…

End-to-end speech-in speech-out dialogue systems are emerging as a powerful alternative to traditional ASR-LLM-TTS pipelines, generating more natural, expressive responses with significantly lower latency. However, these systems remain…

Large language model (LLM) serving is becoming an increasingly critical workload for cloud providers. Existing LLM serving systems focus on interactive requests, such as chatbots and coding assistants, with tight latency SLO requirements.…

Full-stream text-to-speech (TTS) for interactive systems must start speaking with minimal delay while remaining controllable as text arrives incrementally. We present VoXtream2, a zero-shot full-stream TTS model with dynamic speaking-rate…

This paper presents ServerlessLLM, a distributed system designed to support low-latency serverless inference for Large Language Models (LLMs). By harnessing the substantial near-GPU storage and memory capacities of inference servers,…

Deploying conversational voice agents with large language models faces a critical challenge: cloud-based foundation models provide deep reasoning and domain knowledge but introduce latency that disrupts natural conversation, while on-device…

We present a multimodal fusion framework that bridges pre-trained decoder-based large language models (LLM) and acoustic encoder-decoder architectures such as Whisper, with the aim of building speech-enabled LLMs. Instead of directly using…

Recently sequence-to-sequence models have started to achieve state-of-the-art performance on standard speech recognition tasks when processing audio data in batch mode, i.e., the complete audio data is available when starting processing.…

Diffusion-based video super-resolution (VSR) methods deliver strong perceptual quality but are often unsuitable for latency-sensitive scenarios due to reliance on future frames and expensive multi-step denoising. We propose Stream-DiffVSR,…