论文解读
The SonicAGI System for the REAL-TSE Challenge
语音分离 | 6.8/10
流式处理
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
Metronome: Bound the Cache, Keep the Beat for Real-Time Interaction Model Serving
语音交互 | 8.7/10
论文解读
SPEARBench: A Benchmark for Naturalness Evaluation in Streaming Speech-to-Speech Language Models
语音交互 | 8.9/10
论文解读
Streaming Neural Speech Codecs through Time-Invariant Representations
语音编码 | 6.0/10
论文解读
Wan-Streamer v0.2: Higher Resolution, Same Latency
音视频交互 | 5.4/10
论文解读
PhoStream: Benchmarking Real-World Streaming for Omnimodal Assistants in Mobile Scenarios
音视频问答 | 7.3/10
论文解读
ProactiveLLM: Learning Active Interaction for Streaming Large Language Models
语音识别 | 7.2/10
论文解读
Query-Based Asymmetric Modeling with Decoupled Input–Output Rates for Speech Restoration
语音增强 | 7.1/10
论文解读
Scaling Transformers for End-to-End Discrete Audio Tokenization
音频编码 | 7.1/10
论文解读
Simultaneous Speech-to-Speech Translation Without Aligned Data
语音翻译 | 8/10
论文解读
Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage
流式处理 | 7.2/10
论文解读
The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning
知识蒸馏 | 7/10
论文解读
Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion Transformer
音视频生成 | 6.6/10
论文解读
video-SALMONN S: Memory-Enhanced Streaming Audio-Visual LLM
音视频问答 | 7.3/10
论文解读
Latency-Configurable Streaming Speech Enhancement via Asymmetric Temporal Padding
语音增强 | 7.2/10
论文解读
MaineCoon: Pursuing A Real-Time Audio-Visual Social World Model
语音合成 | 5.7/10
论文解读
Zero-VC: Zero-Lookahead Streaming Voice Conversion via Speaker Anonymization
语音转换 | 6.1/10
论文解读
Next-Turn: Duration-Aware Streaming Endpoint Detection via Time-to-Next-Speech-Onset Prediction
语音合成 | 7.9/10
论文解读
Efficiency-Performance Trade-offs in Neural Speaker Diarization via Structured Pruning and Low-Bit Quantization
说话人日志 | 5.1/10