论文解读
TurboBias 2.0: Streaming Context-Biasing for Production-Efficient ASR Systems
语音识别 | 9.0/10
流式处理
论文解读
X2Streaming-TTS: Causal Token-Level Text-to-Speech from Streaming Text with Speech-State Inheritance
语音合成 | 7.9/10
论文解读
DNN-Based Frequency-Dependent Estimation of Speech, Music, and Noise Power in Acoustic Mixtures for Hearing-Aid Scene Analysis
音频分离 | 6.5/10
论文解读
Target Speaker Identification: A Low-Latency Streaming Pipeline
说话人验证 | 5.6/10
论文解读
StreamHear: Domain-Adapted Pseudo-Labeling for Semi-Supervised Streaming Speech Recognition
语音识别 | 6.4/10
论文解读
VoiceChat-TTS: A Low-Latency Continuous Speech Synthesis Model for Interactive Agents
语音合成 | 8.2/10
论文解读
Luna-TTS Family Technical Report
语音合成 | 6.9/10
论文解读
RT-SEMamba: Real-Time Speech Enhancement Mamba via Progressive Knowledge Distillation
语音增强 | 6.6/10
论文解读
Vorch-Streamer: Extending Human Audio-Visual Generation to Real-Time Long-Form Streaming
音视频生成 | 7.4/10
论文解读
Homebot: A Personal AI Agent for Conversational Home Assistance and Automation
语音交互 | 3.8/10
论文解读
LeapTalk: Breaking the Latency-Quality Trade-off in Talking Head Generation
音视频生成 | 6.8/10
论文解读
WeSep: A Modular and Cue-Composable Framework for Target Speaker Extraction
语音分离 | 7.4/10
论文解读
faster-enhancer.c: A Dependency-Free int8 Runtime for Streaming Speech Enhancement on Commodity CPUs
语音增强 | 8.7/10
论文解读
Low-Latency Turn-Taking via Context-Aware Preface Generation in a Real-World Dialogue Robot
语音交互 | 6.1/10
论文解读
CODA: Cascaded Online Discontinuity-Aware Alignment for Real-Time Image-Based Score Following
音频理解 | 8.1/10
论文解读
Faster IndexTTS-2: Accelerating and Streaming Autoregressive Zero-Shot Text-to-Speech Synthesis on GPUs
语音合成 | 7.6/10
论文解读
Safeguards for Speech2Speech LLM-Assistants: A Case Study in Automotive Applications
语音交互 | 6.5/10
论文解读
CAPS: A Cascaded Reconstruction Model to Power Saving in Hearables Using Sub-Nyquist Sampling with Bandwidth Extension
语音增强 | 6.6/10
论文解读
Cumsum-Composable Phase Transport for Low-Cost Streaming Keyword Spotting
语音唤醒 | 5.9/10
论文解读
SimulS2ST-Omni: Data-Efficient Streaming Speech-to-Speech Translation via Explicit Trajectory Supervision
语音翻译 | 7.3/10