论文解读
Streaming T5-based Text-to-Speech Synthesis with Limited Lookahead
语音合成 | 6.7/10
语音合成
论文解读
Synthesizing the Lombard Effect: Multi-Level Control of Speech Clarity and Vocal Effort in TTS
语音合成 | 7.2/10
论文解读
Word Lengthening as a Function of Utterance Position: A Multi-Corpus Study
语音合成 | 8.1/10
论文解读
A Survey of Full-Duplex Spoken Dialogue Systems: Architectural Hierarchy, Interaction Ontology, and Decision State Machine
语音合成 | 7.4/10
论文解读
FlowEdit: Associative Memory for Lifelong Pronunciation Adaptation in Flow-Matching TTS
语音合成 | 10/10
论文解读
How Do Instructions Shape Speech? Cross-Attention Attribution for Style-Captioned Text-to-Speech
语音合成 | 7.7/10
论文解读
Improving Code-Switching ASR with Code-Mixing Guided Synthetic Speech
语音识别 | 7.6/10
论文解读
Interpreting Content and Speaker Characteristics in Factorised Self-Supervised Subspaces
语音合成 | 5/10
论文解读
Investigating Human-Model Discrepancies in Speech Quality Assessment via Acoustic and Prosodic Perturbations
语音合成 | 6.9/10
论文解读
Low-Burden Data Augmentation for Dysarthric ASR via Zero-Shot Voice Cloning
语音识别 | 8.7/10
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
PhysDrift: Bridging the Embodiment Gap in Humanoid Co-Speech Motion Generation
语音合成 | 7.4/10
论文解读
ReNikud: Audio-Supervised Hebrew Grapheme-to-Phoneme Conversion
语音合成 | 6.2/10
论文解读
Repurposing a Speech Classifier for Guided Diffusion-Based Speech Generation
语音合成 | 7.9/10
论文解读
Transcript-Free Flow-Matching Text-to-Speech via Speech Feature Conditioning
语音合成 | 7.7/10
论文解读
FineCombo-TTS: Collaborative and Precise Controllable Speech Synthesis Using Text Descriptions and Reference Speech
语音合成 | 7.6/10
论文解读
GRIDEX: Grid-Grounded Forensic Explanations for Deepfake Spectrogram Analysis
语音合成 | 8.6/10
论文解读
MagpieTTS-LF: Inference-Time Long-Form Speech Generation Without Training on Long-Form data
语音合成 | 7.9/10
论文解读
Reference-Driven Multi-Speaker Audio Scene Generation from In-the-Wild Priors
语音合成 | 7.3/10
论文解读
Reliable Neural-Codec Text-to-Speech by ASR Self-Verification and Distillation: Near-Zero Catastrophic Failures Across Models and Codecs
语音合成 | 7.4/10