论文解读
Compress the Cache, Not the Speech Embedding: KV Compression for Efficient Speech LLMs
语音识别 | 7/10
语音大模型
论文解读
Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs
语音识别 | 7.3/10
论文解读
Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMs
语音交互 | 9.2/10
论文解读
WordVoice: Explicit and Decoupled Multi-Dimensional Word-Level Control for LLM-Based TTS
语音合成 | 7.2/10
论文解读
Reinforcement Learning for Data-Efficient Code-Switched ASR
语音识别 | 5.3/10
论文解读
Speaker-Disentangled Chunk-Wise Regression for Syllabic Tokenization
语音编码 | 7.9/10
论文解读
\(\tau\)-Voice: Benchmarking Full-Duplex Voice Agents on Real-World Domains
语音交互 | 9.1/10
论文解读
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability
语音合成 | 6.6/10
论文解读
LALM-as-a-Judge: Benchmarking Large Audio-Language Models for Safety Evaluation in Multi-Turn Spoken Dialogues
语音交互 | 8.1/10
论文解读
Unlocking Speech–Text Compositional Powers: Instruction-Following Speech Language Models without Instruction Tuning
语音交互 | 6.7/10
论文解读
NAVER LABS Europe Submission to the Instruction-following 2026 Short Track
语音翻译 | 6.2/10
论文解读
Unlocking Speech-Text Compositional Powers: Instruction-Following Speech Language Models without Instruction Tuning
语音交互 | 8.5/10
论文解读
Preference-ASR: A Preference-Aware Test Set for Benchmarking ASR in the Era of Speech LLMs
语音识别 | 9.5/10
论文解读
Codec-Robust Attacks on Audio LLMs
音频安全 | 8.3/10
论文解读
Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation
语音识别 | 9.3/10
论文解读
Synchronization and Turn-Taking in Full-Duplex Speech Dialogue Models
语音对话系统 | 7.6/10
论文解读
FormalASR: End-to-End Spoken Chinese to Formal Text
语音识别 | 6/10
论文解读
Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation
语音识别 | 6.8/10
论文解读
Can Large Audio Language Models Ignore Multilingual Distractors? An Evaluation of Their Selective Auditory Attention Capabilities
音频问答 | 6.5/10
论文解读
From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents
模型评估 | 6.3/10