论文解读
AOR-Bench: Do Large Audio Language Models Over-Refuse Pseudo-Harmful Queries?
音频问答 | 7.9/10
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
ATCCaps: A Call-Sign-Aware Speech Dataset for Air Traffic Control Recognition
语音识别 | 8.6/10
论文解读
CAAD: Contrastive Audio-Aware Distillation for Efficient Speech Language Models
语音识别 | 8.9/10
论文解读
CORTIS: Text-Only Adaptation of Spoken Language Models for Task-Oriented Voice Agents
语音识别 | 7.7/10
论文解读
DisSpeech: Low-Resource Controllable Mandarin Stuttered Speech Synthesis for ASR Augmentation
语音合成 | 7.2/10
论文解读
ESPnet3: Infrastructure for Scalable Speech and Audio Research in the Foundation Model Era
语音识别 | 7.5/10
论文解读
From Text Metrics to Model Internals: A Study of Whisper ASR Hallucination Detection
语音识别 | 7.5/10
论文解读
HALAS: A Human-Annotated Dataset of Hallucinations of Modern ASR Systems
语音识别 | 8.4/10
论文解读
Interleaved Speech Language Models Latently Work In Text
语音识别 | 6.4/10
论文解读
ISCSLP 2026 CoT-TTS Challenge: Chain-of-Thought Reasoning for Context-Aware Text-to-Speech
语音合成 | 6.6/10
论文解读
MindAlign: Decoding Inner Speech from fMRI Signals via Multimodal Embedding Alignment under Limited Data
语音识别 | 5.8/10
论文解读
Online Predictive Coding for Dual-Mode Self-Supervised Speech Model
语音识别 | 7.2/10
论文解读
OpenWER: Improving Cross-Lingual ASR Evaluation and Enabling Token-Based Accuracy Metrics
语音识别 | 8/10
论文解读
Scaling Audio Models Efficiently: A Joint Study of Compute Constraints and Optimization Behavior
语音识别 | 7.2/10
论文解读
The Anatomy of the CTC Oracle Gap: Acoustic Exhaustion and Linguistic Recovery
语音识别 | 7.3/10
论文解读
Time-Frequency Weighted Losses for Phoneme Reconstruction in DNN-Based Speech Enhancement
语音增强 | 7.8/10
论文解读
Using Phonological-Level Wav2Vec2 for Mandarin Automatic Mispronunciation Detection and Diagnosis
语音识别 | 8.3/10
论文解读
Vaani Benchmark V1.0: An Inclusive Multimodal Benchmark Dataset for Hindi
语音识别 | 6.7/10
论文解读
Word Lengthening as a Function of Utterance Position: A Multi-Corpus Study
语音合成 | 8.1/10
论文解读
A Comparative Study of Pretrained Transformer Models for Quranic ASR: Speech Representations, Label Formats, and Dataset Composition
语音识别 | 7.2/10