Roadmap towards Advanced Speech Understanding using Large Language Models
Abstract: The success of large language models (LLMs) has prompted efforts to integrate speech and audio data, aiming to create general foundation models capable of processing both textual and non-textual inputs. Recent advances, such as GPT-4o, highlight the potential for end-to-end speech LLMs, which preserves non-semantic information and world knowledge for deeper speech understanding.
To guide the development of speech LLMs, we propose a five-level roadmap, ranging from basic automatic speech recognition (ASR) to advanced superhuman models capable of integrating non-semantic information with abstract acoustic knowledge for complex tasks.
Moreover, we design a benchmark, \textbf{Roadmap Bechmark}, that standardizes critical aspects across various tasks in these five levels, uncovering challenges in using abstract acoustic knowledge and completeness of capability.
Our findings reveal gaps in handling paralinguistic cues and abstract acoustic knowledge, and we offer future directions. This paper outlines a roadmap for advancing speech LLMs, introduces a benchmark for evaluation, and provides key insights into their current limitations and potential.
Paper Type: Long
Research Area: Multimodality and Language Grounding to Vision, Robotics and Beyond
Research Area Keywords: Large langauge models; speech language models
Contribution Types: Model analysis & interpretability, Data resources, Theory
Languages Studied: English，Chinese
Submission Number: 1001
Loading