论文解读
LLM can Read Spectrogram: Encoder-free Speech-Language Modeling
语音识别 | 8.6/10
参数高效微调
论文解读
ParaBridge: Bridging Paralinguistic Perception and Dialogue Behavior in Speech Language Models
参数高效微调 | 8.6/10
论文解读
Phoneme-First Prediction for LLM-Based Speech Recognition
语音识别 | 6.9/10
论文解读
RespiraMFM: A Multimodal Foundation Model with Contrastive Audio-Language Alignment for Respiratory Disease Identification
对比学习 | 6.5/10
论文解读
Speech Encoder Fusion for LLM-based Automatic Speech Recognition
语音识别 | 7.2/10
论文解读
Towards Deep Contextual Reasoning from Broad Descriptions for ASR with Speech-LLM via Metadata-Driven Reasoning Chains
语音识别 | 6.2/10
每日研究速递
语音/音乐/音频论文速递 2026-06-10
共分析 45 篇语音/AI 论文
论文解读
Rethinking Depth: A study of the Recursive-Transformer for Speech Recognition
语音识别 | 7.5/10
论文解读
Subtitle-Aligned Fine-Tuning of Whisper for Swiss German ASR: Benchmark Contamination, Convention Mismatch, and an Honest Baseline at 25.6% WER (13.8% cWER)
语音识别 | 8.2/10
论文解读
TLDR: Compressing Audio Tokens for Efficient Autoregressive Text-to-Speech
语音合成 | 8.2/10
每日研究速递
语音/音乐/音频论文速递 2026-06-09
共分析 48 篇语音/AI 论文
论文解读
Acoustic Cue Alignment in Audio Language Models for Speech Emotion Recognition
语音情感识别 | 7.8/10
论文解读
Beyond Semantic Dominance: Cognitive Affective Reasoning and Empathetic Response Alignment in Audio Language Models
语音合成 | 9.2/10
论文解读
How Far Can Chord-Symbol Time-Series Adaptation Carry Genre Identity? Capabilities and Boundaries in Multi-Genre Chord-Symbol Modeling
音乐信息检索 | 8.8/10
论文解读
KIT's Submission to Cross-Lingual Voice Cloning in IWSLT 2026
语音合成 | 7.2/10
论文解读
SpectCount: Spectrotemporal Counting via Synthetic Signals Improves Large Audio Language Models
数据增强 | 5.5/10
每日研究速递
语音/音乐/音频论文速递 2026-06-08
共分析 38 篇语音/AI 论文
论文解读
Age-Aware Adapter Tuning for Children's Speech Recognition
语音识别 | 8.4/10
论文解读
Beyond Generative Decoding: Discriminative Hidden-State Readout from a Native Omni-Modal LLM for Multimodal Sentiment Analysis
多模态模型 | 5.3/10
论文解读
FiLM-Based Speaker Conditioning of a SpeechLLM for Pathological Speech Recognition
语音识别 | 8.0/10