论文解读
UrduSpeech: A 156-Hour Urdu Speech Corpus with 12-Dimension Paralinguistic Annotations
语音识别 | 7/10
多语言
子标签
下方只统计已核验方向的论文记录，按已核身份去重，身份待核时按页面保留。“直接”只含明确标注该方向的论文；“含子树”同时包含下级方向。点击名称进入论文库继续筛选；数量与上方按标签名称收录的页面数不同。
- 代码转换 直接 14 篇 · 含子树 14 篇
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
论文解读
Refining Pseudo-Audio Prompts with Speech-Text Alignment for Text-Only Domain Adaptation in LLM-Based ASR
语音识别 | 7.5/10
论文解读
Streaming Speech-to-Text Translation with a SpeechLLM
语音翻译 | 6.8/10
每日研究速递
语音/音乐/音频论文速递 2026-05-15
共分析 20 篇语音/AI 论文
论文解读
Does language matter for spoken word classification? A multilingual generative meta-learning approach
音频分类 | 6.0/10
论文解读
Vividh-ASR: A Complexity-Tiered Benchmark and Optimization Dynamics for Robust Indic Speech Recognition
语音识别 | 7.0/10
论文解读
Mechanistic Interpretability of ASR models using Sparse Autoencoders
语音识别 | 5.5/10
论文解读
Mind the Pause: Disfluency-Aware Objective Tuning for Multilingual Speech Correction with LLMs
语音编辑 | 6.5/10
论文解读
Towards Fine-Grained Multi-Dimensional Speech Understanding: Data Pipeline, Benchmark, and Model
Towards Fine-Grained Multi-Dimensional Speech Understanding: Data Pipeline, Benchmark, and Model
论文解读
What makes a word hard to learn? Modeling L1 influence on English vocabulary difficulty
词汇难度预测 | 5.0/10
论文解读
Dolphin-CN-Dialect: Where Chinese Dialects Matter
语音识别 | 5.5/10
论文解读
RADAR Challenge 2026: Robust Audio Deepfake Recognition under Media Transformations
音频深度伪造检测 | 6.0/10
论文解读
Rethinking Entropy Minimization in Test-Time Adaptation for Autoregressive Models
语音识别 | 6.0/10
论文解读
Linear Semantic Segmentation for Low-Resource Spoken Dialects
语义分割 | 7.5/10
论文解读
MultiLinguahah : A New Unsupervised Multilingual Acoustic Laughter Segmentation Method
音频事件检测 | 8.5/10
论文解读
X-Voice: Enabling Everyone to Speak 30 Languages via Zero-Shot Cross-Lingual Voice Cloning
语音克隆 | 8.0/10
论文解读
MiniMind-O Technical Report: An Open Small-Scale Speech-Native Omni Model
语音对话系统 | 7.5/10
论文解读
The TTS-STT Flywheel: Synthetic Entity-Dense Audio Closes the Indic ASR Gap Where Commercial and Open-Source Systems Fail
语音识别 | 8.5/10
每日研究速递
语音/音乐/音频论文速递 2026-05-07
共分析 22 篇语音/AI 论文