论文解读
Hearing Without Noticing? Attention-Aware Stealthy Black-Box Adversarial Audio Attacks
语音识别 | 7.6/10
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
Joint Enhancement and Classification using Coupled Diffusion Models of Signals and Logits
语音识别 | 9.3/10
论文解读
NeuroCLUS: A Foundation Model with Functional Clustering for Intracranial Neural Decoding
语音识别 | 6/10
论文解读
ProactiveLLM: Learning Active Interaction for Streaming Large Language Models
语音识别 | 7.2/10
论文解读
Scaling Transformers for End-to-End Discrete Audio Tokenization
音频编码 | 7.1/10
论文解读
SPEAR: A Unified SSL Framework for Learning Speech and Audio Representations
音频理解 | 8.4/10
论文解读
WaveSSM: Multiscale State-Space Models for Non-stationary Signal Attention
音频分类 | 4.8/10
论文解读
An Efficient vLLM-Based Inference Pipeline for Unified Audio Understanding and Generation
语音合成 | 6.8/10
论文解读
Beyond Words: Towards Effective Modeling of Non-Verbal Vocalizations in ASR
语音识别 | 6.4/10
论文解读
From Monolingual to Multilingual: Evaluating Mamba for ASR in South African Languages
语音识别 | 4.8/10
论文解读
H-SAGE: Holistic Speaker-Aware Guided Experts for MoE-based Multi-Talker ASR
语音识别 | 6.9/10
论文解读
NAVER LABS Europe Submission to the Instruction-following 2026 Short Track
语音翻译 | 6.2/10
论文解读
Spatial Speech Perception Systems: A Survey of Sound Source Localization, Directional Enhancement, and Speech Recognition
声源定位 | 4.1/10
论文解读
NPUsper: Eliminating Redundant Computation for Real-Time Whisper on Mobile NPUs
语音识别 | 9/10
论文解读
Adapting Foundation ASR Models to Dysarthric Speech: A Case Study
语音识别 | 6.2/10
论文解读
BEST-RQ-2: Contextualize-Then-Predict, a Two-Step Approach for Self-Supervised Audio Representations
语音识别 | 6.9/10
论文解读
Building a Multimodal Dataset of Academic Paper for Keyword Extraction
语音识别 | 5.2/10
论文解读
Building an ASR Solution for Training and Assessing Children's Reading
语音识别 | 8.5/10
论文解读
Enhancing BEST-RQ Pseudo-Label Quality through Online Refinement for Automatic Speech Recognition
语音识别 | 8.6/10
论文解读
FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model
语音合成 | 7.2/10