论文解读
Improving multichannel speech enhancement through accurate room-acoustic simulations
语音增强 | 6.8/10
语音识别
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。
论文解读
LuxEmo: Expressive Text-to-Speech Corpus for Luxembourgish
语音合成 | 7.5/10
论文解读
Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation
语音识别 | 7/10
论文解读
Tone-Conditioned Curriculum Learning for Low-Resource Bantu Speech Recognition
语音识别 | 7.3/10
论文解读
What Counts as an Error? Dual-Reference Benchmarking for Atypical ASR
语音识别 | 7.3/10
论文解读
Agent-Computer Observation Interfaces Enable Dynamic Computer Use
语音识别 | 8.4/10
论文解读
AMR: Adaptive Modality Routing for Multimodal Polyglot Speaker Identification
说话人识别 | 7.8/10
论文解读
Comparing Human and Automatic Recognition of Dutch Dysarthric Continuous Speech: A Case Study
语音识别 | 6.5/10
论文解读
CTC-Seeded Token Edit Refinement for Non-Autoregressive Speech Recognition
语音识别 | 7.7/10
论文解读
DialogPII: A multilingual dataset of synthetic dialog transcripts to detect personal information
语音识别 | 8.9/10
论文解读
GigaSpeechBench: A Real-World Multilingual Speech-to-Text Benchmark
语音识别 | 8.7/10
论文解读
How to Leverage Synthetic Speech for LLM-Based ASR Systems?
语音识别 | 8.7/10
论文解读
Position-Aware Target Speaker Extraction for Long-Form Multi-Party Conversations: A Diarization-Free Framework for ASR
语音识别 | 8.5/10
论文解读
Preference-ASR: A Preference-Aware Test Set for Benchmarking ASR in the Era of Speech LLMs
语音识别 | 9.5/10
论文解读
VIB-AVSR: Variational Information Bottleneck for Noise-Robust LLM-Based Audio-Visual Speech Recognition
语音识别 | 9/10
论文解读
A Survey of Automated Presentation Coaching: Systems, Methods, and Open Challenges
语音识别 | 5.4/10
论文解读
Do Speech Emphasis Models Generalize across Languages and Emotions?
语音识别 | 7/10
论文解读
From Black-Box to Clinical Insight: A Multi-Stage Explainable Framework for Speech-Based Cognitive Impairment Detection
语音识别 | 6/10
论文解读
HPRO: Hierarchical Progressive Reward Optimization via Preference Extraction for Emotional Text-to-Speech
语音合成 | 8.2/10
论文解读
HybridCodec: Modeling Discrete and Continuous Representations for Efficient Speech Language Models
语音合成 | 6.5/10