Why Do Speech Language Models Fail to Generate Semantically Coherent Outputs? A Modality Evolving Perspective
원문 초록
Although text-based large language models exhibit human-level writing ability and remarkable intelligence, speech language models (SLMs) still struggle to generate semantically coherent outputs. There are several potential reasons for this performance degradation: (A) speech tokens mainly provide phonetic information rather than semantic information, (B) the length of speech sequences is much longer than that of text sequences, and (C) paralinguistic information, such as prosody, introduces additional complexity and variability. In this paper, we explore the influence of three key factors separately by transiting the modality from text to speech in an evolving manner. Our findings reveal that the impact of the three factors varies. Factor A has a relatively minor impact, factor B influences syntactical and semantic modeling more obviously, and factor C exerts the most significant impact, particularly in the basic lexical modeling. Based on these findings, we provide insights into the unique challenges of training SLMs and highlight pathways to develop more effective end-to-end SLMs.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching
Differentiable Reward Optimization for LLM based TTS system
PresentAgent: Multimodal Agent for Presentation Video Generation
RapFlow-TTS: Rapid and High-Fidelity Text-to-Speech with Improved Consistency Flow Matching
InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems
ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching
토론
이 논문과 연결된 포럼 글이 아직 없습니다.