论文解读

NaturalFlow: Reducing Disruptive Pauses for Natural Speech Flow in Simultaneous Speech-to-Speech Translation

语音翻译 | 7/10

 · 更新于 2026-09-24 · 约 10 分钟 · 4630 字 阅读 →
论文解读

Speech Meets ELF: Audio Conditional Continuous-Target Diffusion for Speech Recognition and Translation

语音识别 | 8.3/10

 · 更新于 2026-09-24 · 约 13 分钟 · 6269 字 阅读 →
论文解读

Ouvia: A User-centered Framework for Measuring Usability of Speech Translation in Real-World Communication Scenarios

语音翻译 | 8.6/10

 · 更新于 2026-09-24 · 约 12 分钟 · 5825 字 阅读 →
论文解读

Multilingual Long-Form Speech Instruction Following: KIT's Submission to IWSLT 2026

语音识别 | 10/10

 · 更新于 2026-09-24 · 约 13 分钟 · 6280 字 阅读 →
论文解读

A Pocket Offline Model for Simultaneous Speech Translation as CUNI Submission to IWSLT 2026

语音翻译 | 6.8/10

 · 更新于 2026-09-24 · 约 13 分钟 · 6364 字 阅读 →
论文解读

AlignAtt4LLM: Fast AlignAtt for Decoder-Only LLMs at IWSLT 2026 Simultaneous Speech Translation Task

语音翻译 | 7.3/10

 · 更新于 2026-09-24 · 约 14 分钟 · 6725 字 阅读 →
论文解读

A Unified and Reproducible Experimentation Framework for Speech Understanding

语音识别 | 5.5/10

 · 更新于 2026-09-24 · 约 13 分钟 · 6336 字 阅读 →
论文解读

DOA: Training-Free Decoder-Only Attention Policy for Long-Form Simultaneous Translation with SpeechLLMs

语音翻译 | 7.8/10

 · 更新于 2026-09-24 · 约 12 分钟 · 5915 字 阅读 →
论文解读

OpenSTBench: Beyond Semantic Evaluation for Speech Translation

语音翻译 | 6.0/10

 · 更新于 2026-09-24 · 约 13 分钟 · 6238 字 阅读 →
论文解读

Bandwidth-Efficient and Privacy-Preserving Edge-Cloud Many-to-Many Speech Translation

语音翻译 | 8.1/10

 · 更新于 2026-09-24 · 约 13 分钟 · 6093 字 阅读 →
论文解读

Why We Need Speech to Evaluate Speech Translation

语音翻译 | 8.3/10

 · 更新于 2026-09-24 · 约 13 分钟 · 6500 字 阅读 →
论文解读

From Flat Language Labels to Typological Priors: Structured Language Conditioning for Multilingual Speech-to-Speech Translation

语音翻译 | 6.9/10

 · 更新于 2026-09-24 · 约 36 分钟 · 17909 字 阅读 →
论文解读

Streaming Speech-to-Text Translation with a SpeechLLM

语音翻译 | 6.8/10

 · 更新于 2026-09-24 · 约 22 分钟 · 10616 字 阅读 →
会议任务专题

ICLR 2026 - 语音翻译

共 2 篇 ICLR 2026 语音翻译 方向论文

 · 更新于 2026-09-24 · 约 7 分钟 · 3191 字 阅读 →
论文解读

Scalable Multilingual Multimodal Machine Translation with Speech-Text Fusion

语音翻译 | 8.5/10

 · 更新于 2026-09-24 · 约 10 分钟 · 4966 字 阅读 →
论文解读

UniSS: Unified Expressive Speech-to-Speech Translation with Your Voice

语音翻译 | 8.0/10

 · 更新于 2026-09-24 · 约 9 分钟 · 4434 字 阅读 →
论文解读

MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks

基准测试 | 8.0/10

 · 更新于 2026-09-24 · 约 10 分钟 · 4653 字 阅读 →
论文解读

Scalable Multilingual Multimodal Machine Translation with Speech-Text Fusion

语音翻译 | 8.0/10

 · 更新于 2026-09-24 · 约 13 分钟 · 6243 字 阅读 →
论文解读

UniSS: Unified Expressive Speech-to-Speech Translation with Your Voice

语音翻译 | 7.5/10

 · 更新于 2026-09-24 · 约 11 分钟 · 5273 字 阅读 →
论文解读

Normativity and Productivism: Ableist Intelligence? A Degrowth Analysis of AI Sign Language Translation Tools for Deaf People

语音翻译 | 3.5/10

 · 更新于 2026-09-24 · 约 5 分钟 · 2038 字 阅读 →