论文解读
Sarashina2.2-TTS: Tackling Kanji Polyphony in Japanese Speech Generation via Data Scaling and Targeted Data Synthesis
语音合成 | 7.3/10
语音生成
本索引论文的研究方向
仅取本页论文已有的已核验分类，同一篇论文在每个方向只计一次；多个方向可能重叠。这些关联不表示标签名称与某个研究方向等同。
浏览全部研究方向 →论文解读
On the Effect of Segmentation Width and Cluster Size on Speech Resynthesis and Continuation in Generative Spoken Language Models
语音合成 | 7.4/10
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
MUNI: Multimodal Unified Latent Diffusion for Coherent Any-to-Any Generation
语音生成 | 6.9/10
论文解读
Probing Low Frame Rate Degradation in Neural Audio Codecs
语音生成 | 8.6/10
论文解读
SARA: A Dual-Stream VAE for High-Fidelity Speech Generation via Integrating Semantic and Acoustic Representations
语音合成 | 7.9/10
论文解读
OmniCap-IF: Benchmarking and Improving Instruction Following Abilities for Omni-Video Captioning
语音生成 | 9.1/10
论文解读
OpenBibleTTS: Large-Scale Speech Resources and TTS Models for Low-Resource Languages
语音合成 | 8/10
论文解读
HybridCodec: Fast Dual-Stream, Semantically Enhanced Neural Audio Codec
语音合成 | 5.7/10
论文解读
WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modeling
语音合成 | 9.2/10
论文解读
UniVocal: Unified Speech-Singing Code-Switching Synthesis
语音合成 | 8.9/10
论文解读
MTAVG-Bench 2.0: Diagnosing Failure Modes of Cinematic Expressiveness in Multi-Talker Audio-Video Generation
语音生成 | 9.9/10
论文解读
PilotTTS: A Disciplined Modular Recipe for Competitive Speech Synthesis
语音合成 | 9.2/10
论文解读
WavCube: Unifying Speech Representation for Understanding and Generation via Semantic-Acoustic Joint Modeling
语音生成 | 7.5/10
会议任务专题
ICLR 2026 - 语音生成
共 1 篇 ICLR 2026 语音生成 方向论文
论文解读
TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling
语音生成 | 7.0/10
会议任务专题
ICASSP 2026 - 语音生成
共 1 篇 ICASSP 2026 语音生成 方向论文
论文解读
ReCoM: Realistic Co-Speech Motion Generation with Recurrent Embedded Transformer
音频生成 | 7.0/10
论文解读
Why Do Speech Language Models Fail to Generate Semantically Coherent Outputs? A Modality Evolving Perspective
语音生成 | 7.0/10