论文解读
Group Relative Policy Optimization for Text-to-Speech with Large Language Models
语音合成 | 8.0/10
多语言
论文解读
How Far Do SSL Speech Models Listen for Tone? Temporal Focus of Tone Representation under Low-Resource Transfer
语音识别 | 6.5/10
论文解读
Human-1 by Josh Talks: A Full-Duplex Conversational Modeling Framework in Hindi using Real-World Conversations
语音对话系统 | 7.5/10
论文解读
Improving Contextual Asr Via Multi-Grained Fusion With Large Language Models
语音识别 | 8.5/10
论文解读
Influence of Clean Speech Characteristics on Speech Enhancement Performance
语音增强 | 8.0/10
论文解读
保留高维 XLS-R 特征时单层 KAN 能否以更少参数替代复杂后端
📄 保留高维 XLS-R 特征时单层 KAN 能否以更少参数替代复杂后端 会议论文 ID：conference:icassp:2026:icassp-arnumber:11460320
论文解读
Korean aegyo speech shows systematic F1 increase to signal childlike qualities
语音情感识别 | 6.0/10
论文解读
Language-Infused Retrieval-Augmented CTC with Adaptive Soft-Hard Gating for Robust Code-Switching ASR
语音识别 | 8.0/10
论文解读
LESS: Large Language Model Enhanced Semi-Supervised Learning for Speech Foundational Models Using in-the-wild Data
语音识别 语音翻译 | 7.5/10
论文解读
Leveraging Audio-Visual Data to Reduce the Multilingual Gap in Self-Supervised Speech Models
语音识别 | 6.0/10
论文解读
Leveraging Whisper Embeddings For Audio-Based Lyrics Matching
音乐信息检索 | 7.0/10
论文解读
LongSpeech: A Scalable Benchmark for Transcription, Translation and Understanding in Long Speech
基准测试 | 7.8/10
论文解读
Low-Resource Speech-Based Early Alzheimers Detection via Cross-Lingual and Few-Shot Transfer Learning
语音生物标志物 | 7.5/10
论文解读
Mixtures of Lightweight Articulatory Experts for Multilingual Asr
语音识别 | 7.0/10
论文解读
MTP-S2UT: Enhancing Speech-to-Speech Translation Quality with Multi-Token Prediction
语音翻译 | 8.5/10
论文解读
Multilingual Supervised Pretraining with Lm-Assisted Decoding for Visual Speech Recognition
语音识别 | 6.5/10
论文解读
Natural Language to Spatial Audio Parameters: Lightweight Deterministic Rendering for Creative Authoring
空间音频 | 7.5/10
论文解读
NCF-TTS: Enhancing Flow Matching Based Text-To-Speech with Neighborhood Consistency Flow
语音合成 | 8.0/10
论文解读
nGPT as a Scalable Architecture for Speech Recognition and Translation
语音识别 | 7.5/10
论文解读
PAC: Pronunciation-Aware Contextualized Large Language Model-Based Automatic Speech Recognition
语音识别 | 7.0/10