论文解读
同样的两段声音，为何转写稳得住、问答就垮掉？
音频理解 | 6.1/10
语音识别
论文解读
同音不同形，真的同音吗？当语义在频谱里留下指纹
语音识别 | 6.8/10
论文解读
合成语音越多越好吗？在音素层面重新称量文本的价值
语音识别 | 6.2/10
论文解读
把嘴边的电极收回指尖：按需贴合如何让无声语音既可用又不打扰隐私
语音识别 | 5.9/10
论文解读
把电话声道和业务词汇分开付账：Canary 的两次适配实验
语音识别 | 7.9/10
论文解读
32 分钟语料能给 Baniwa ASR 一个起点，却不能借此跳过泛化检验
语音识别 | 4.7/10
论文解读
忘掉不等于擦除：语音网络把关键期痕迹压在了最底层
语音识别 | 8.6/10
论文解读
谐音不是错字：让普通话 ASR 在纠错与保留笑点之间踩刹车
语音识别 | 5.7/10
论文解读
Relative Time Intervals Representation for Word-level Timestamping with Masked Training
语音识别 | 8.6/10
论文解读
Better Retrieval, Worse Robustness: How Multi-hop RAG Amplifies Upstream ASR Errors
音频理解 | 9.1/10
论文解读
Cross-Subject Generalization in Decoding Perceived Speech from Non-Invasive Brain Recordings
语音识别 | 8.3/10
论文解读
Development and Feasibility Evaluation of an Edge AI as Medical Device System for Breast Cancer Multidisciplinary Team Meetings
语音识别 | 8.4/10
论文解读
DiaScriber: A Speech LLM for Joint Diarization and Transcription in Multi-Speaker Scenarios
语音识别 | 7.3/10
论文解读
Mitigating Speaker Leakage in Cascaded Multi-talker ASR with Diarization-based Transcript Correction
语音识别 | 7.1/10
论文解读
Motion-Aware Reasoning from Speech to Mask Tracks: Runner-up Solution for the MeViS-Audio Track of the 8th LSVOS Challenge 2026
音视频理解 | 7.1/10
论文解读
Multi-Task Learning for Non-Canonical Phoneme Recognition via Articulatory Feature Decomposition
语音识别 | 8.2/10
论文解读
TurboBias 2.0: Streaming Context-Biasing for Production-Efficient ASR Systems
语音识别 | 9.0/10
论文解读
Unsupervised Speech Recognition at the Syllable Level
语音识别 | 8.9/10
论文解读
A Speech Corpus for Mizo Automatic Speech Recognition: Whisper and SraVaani 1.0 Fine-Tuning with Morphology-Aware Evaluation
语音识别 | 6.7/10
论文解读
Towards Quantifying Benchmark Optimization in ASR Models
语音识别 | 8.5/10