Research Papers 论文研究 6h ago Updated 2h ago 更新于 2小时前 50

Listen to the Latents: Self-Correcting Speech Recognition in Large Audio Language Models Through Hidden-State Interactions 倾听潜在层:通过隐状态交互实现大型音频语言模型的自校正语音识别

Proposes Hybrid Search, a targeted self-correction strategy for LLM-based ASR that leverages preserved base LLMs during LoRA-adapted inference Introduces interaction features measuring the relationship between ASR hidden states and base-LLM hidden states as signals for token-level semantic dependence Selectively refining high-dependence tokens significantly outperforms naive global correction methods like rescoring and late fusion Demonstrates that warm-initialized LLM-based ASR models retain la 提出Hybrid Search策略,通过隐状态交互实现LLM-based ASR模型的自校正 利用LoRA-adapted设置保留base LLM,结合warm initialization和base LLM的双重优势 通过交互特征识别高语义依赖token,选择性精炼而非全局校正 证明即使warm initialization后,base LLM仍可在推理时进一步提升性能 优于传统的rescoring和late fusion等全局LLM校正方法

70
Hot 热度
75
Quality 质量
72
Impact 影响力

Analysis 深度分析

TL;DR

  • Proposes Hybrid Search, a targeted self-correction strategy for LLM-based ASR that leverages preserved base LLMs during LoRA-adapted inference
  • Introduces interaction features measuring the relationship between ASR hidden states and base-LLM hidden states as signals for token-level semantic dependence
  • Selectively refining high-dependence tokens significantly outperforms naive global correction methods like rescoring and late fusion
  • Demonstrates that warm-initialized LLM-based ASR models retain latent capacity to benefit from their pre-adaptation base LLMs at inference time
  • Bridges the gap between external logit fusion and internal warm initialization strategies in LLM-integrated ASR systems

Why It Matters

This work addresses a critical practical question for AI practitioners building speech recognition systems: how to maximize the utility of large language models without discarding the semantic knowledge embedded in the base LLM during adaptation. The Hybrid Search approach offers a computationally efficient alternative to expensive rescoring or late fusion pipelines, making it more viable for production ASR systems. For researchers, it opens a new direction in understanding how hidden-state interactions can serve as reliable signals for targeted model refinement.

Technical Details

  • Hybrid Search mechanism: A targeted correction strategy that identifies tokens with high semantic dependence by computing interaction features between the LoRA-adapted ASR model's hidden states and the preserved base LLM's hidden states, then selectively refines only those tokens rather than applying global correction.
  • LoRA-adapted setting: The approach operates under low-rank adaptation where the base LLM weights are preserved alongside the adapted ASR weights, enabling the model to access both adapted and pre-adaptation representations simultaneously during inference.
  • Interaction features: Novel features characterizing the relationship/distance between ASR hidden states and base-LLM hidden states serve as proxies for semantic dependence, guiding which tokens benefit most from base-LLM correction.
  • Benchmark comparisons: Evaluated against global LLM-correction baselines including rescoring and late fusion, demonstrating that selective token refinement yields substantially better ASR performance than naive full-sequence correction approaches.

Industry Insight

  • Organizations deploying LLM-based ASR should consider preserving base model weights during adaptation rather than fully fine-tuning, as the retained base LLM can provide meaningful inference-time corrections through interaction-based refinement.
  • Targeted, token-level correction strategies like Hybrid Search offer a compelling efficiency-accuracy tradeoff for production speech systems, reducing computational overhead compared to full rescoring pipelines while achieving superior results.
  • The finding that hidden-state interactions encode useful semantic dependence signals suggests broader applicability beyond ASR—similar approaches could benefit other modalities where LLMs are adapted for specialized tasks while retaining base model knowledge.

TL;DR

  • 提出Hybrid Search策略,通过隐状态交互实现LLM-based ASR模型的自校正
  • 利用LoRA-adapted设置保留base LLM,结合warm initialization和base LLM的双重优势
  • 通过交互特征识别高语义依赖token,选择性精炼而非全局校正
  • 证明即使warm initialization后,base LLM仍可在推理时进一步提升性能
  • 优于传统的rescoring和late fusion等全局LLM校正方法

为什么值得看

这篇论文为ASR与LLM的融合提供了新的技术路径,特别是在LoRA-adapted场景下如何有效利用base LLM的语义知识。对于从事语音识别和语言模型研究的从业者来说,Hybrid Search策略提供了一种高效且精准的推理时校正方法。

技术解析

  • 核心创新:Hybrid Search策略,通过计算LLM-based ASR隐状态与base-LLM隐状态的交互特征,量化token的语义依赖程度
  • 方法特点:选择性精炼高语义依赖的目标token,而非对所有token进行全局校正,显著提升ASR性能
  • 实验设置:基于LoRA-adapted的LLM-based ASR模型,保留base LLM作为参考源
  • 对比方法:与rescoring和late fusion等全局LLM校正方法进行对比实验
  • 关键发现:即使经过warm initialization完成语义知识迁移,base LLM仍能在推理时提供额外的性能提升

行业启示

  • 为ASR与LLM的融合提供了新的技术路径,特别是在推理时的自校正机制,突破了传统全局校正的局限
  • 展示了如何在保持模型效率的同时,充分利用base LLM的语义知识,为语音识别系统的优化提供了新思路
  • 对于LLM在语音领域的应用具有参考价值,特别是在LoRA微调场景下的推理优化策略

Disclaimer: The above content is generated by AI and is for reference only. 免责声明:以上内容由 AI 生成,仅供参考。

Speech 语音 LLM 大模型 Research 科学研究 Training 训练 Inference 推理