论文解读
Int-MeanFlow: Few-Step Speech Generation with Integral Velocity Distillation
语音合成 | 7.5/10
流式处理
论文解读
Integrating Speaker Embeddings and LLM-Derived Semantic Representations for Streaming Speaker Diarization
说话人分离 | 6.5/10
论文解读
Lightweight Phoneme-Conditioned Bandwidth Extension for Body-Conducted Speech
语音增强 | 7.5/10
论文解读
Low-Bandwidth High-Fidelity Speech Transmission with Generative Latent Joint Source-Channel Coding
语音增强 | 7.5/10
论文解读
MeanVC: Lightweight and Streaming Zero-Shot Voice Conversion via Mean Flows
语音转换 | 7.5/10
论文解读
Online Register For Dual-Mode Self-Supervised Speech Models: Mitigating the Lack of Future Context
语音识别 | 6.5/10
论文解读
Phrased: Phrase Dictionary Biasing for Speech Translation
语音翻译 | 7.5/10
论文解读
Real-Time Streaming MEL Vocoding with Generative Flow Matching
语音合成 | 7.5/10
论文解读
SAASDNet: An EEG-Based Streaming Auditory Attention Switch Decoding Network for Self-Initiated Attention Switching in Mixed Speech
脑机接口 | 8.0/10
论文解读
SpatialNet-Echo: Real-Time Acoustic Echo Cancellation via Integrated Narrow-Band and Cross-Band Processing
语音增强 | 7.5/10
论文解读
Spike-Driven Low-Power Speech Bandwidth Extension
语音增强 | 8.0/10
论文解读
Str-DiffSep: Streamable Diffusion Model for Speech Separation
语音分离 | 7.5/10
论文解读
Streaming Speech Recognition with Decoder-Only Large Language Models and Latency Optimization
语音识别 | 7.0/10
论文解读
SynaSpot: A Lightweight, Streaming Multi-modal Framework for Keyword Spotting with Audio-Text Synergy
关键词检测 | 7.5/10
论文解读
Syncspeech: Efficient and Low-Latency Text-to-Speech Based on Temporal Masked Transformer
语音合成 | 7.5/10
论文解读
Train Short, Infer Long: Speech-LLM Enables Zero-Shot Streamable Joint ASR and Diarization on Long Audio
说话人分离 | 9.0/10
论文解读
VChangeCodec: An Ultra Low-Complexity Neural Speech Codec with Built-In Voice Changer for Customized Real-Time Communication
语音转换 语音增强 | 8.0/10
论文解读
VoXtream: Full-Stream Text-To-Speech With Extremely Low Latency
语音合成 | 8.5/10
论文解读
WhisperPipe: A Resource-Efficient Streaming Architecture for Real-Time Automatic Speech Recognition
语音识别 | 6.5/10
论文解读
Hallo-Live: Real-Time Streaming Joint Audio-Video Avatar Generation with Asynchronous Dual-Stream and Human-Centric Preference Distillation
音视频 | 8.5/10