论文解读
Tokenizer Transplantation: Mitigating Autoregressive Collapse in Edge-Efficient Bengali ASR
语音识别 | 8.8/10
语音识别
论文解读
Best-of-N TTS Evaluation is Confounded by ASR Family Alignment
语音合成 | 8.7/10
论文解读
COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation
语音识别 | 8.2/10
论文解读
COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation
语音识别 | 7.5/10
论文解读
Diarization-Guided Qwen-ASR Adaptation for Multilingual Two-Speaker Conversational Speech
语音识别 | 5.7/10
论文解读
Diarization-Guided Qwen-ASR Adaptation for Multilingual Two-Speaker Conversational Speech
语音识别 | 7.0/10
论文解读
On the Role of Conversational Timing in Synthetic Training Data for ASR
语音识别 | 6.4/10
论文解读
On the Role of Conversational Timing in Synthetic Training Data for ASR
语音识别 | 6.6/10
论文解读
Vidu S1: A Real-Time Interactive Video Generation Model
音视频交互 | 5.2/10
论文解读
When Synthetic Speech Is All You Have: Better Call GRPO
语音识别 | 7.7/10
论文解读
When Synthetic Speech Is All You Have: Better Call GRPO
语音识别 | 7.8/10
论文解读
Compress the Cache, Not the Speech Embedding: KV Compression for Efficient Speech LLMs
语音识别 | 7/10
论文解读
Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs
语音识别 | 7.3/10
论文解读
Transformer-based segmentation of prosodic boundaries in Brazilian Portuguese
语音识别 | 4/10
论文解读
UBG-Net: An Uncertainty-aware Bayesian Gating Network for Robust Audio-Visual Speech Recognition
语音识别 | 7.1/10
论文解读
From Sinhala to Dhivehi: Cross-Lingual Transfer Learning for Low-Resource Speech Recognition
语音识别 | 6.6/10
论文解读
Gemma 4 Technical Report
语音识别 | 6.2/10
论文解读
NAVER LABS System Re-implementation for the IWSLT 2026 Instruction-Following Task
语音翻译 | 6.4/10
论文解读
Revisiting the Relation Between Language Model Perplexity and ASR Word Error Rate for Modern End-to-End Speech Recognition
语音识别 | 6/10
论文解读
CHILDES-Aligned: A Curated Children's Speech Dataset via Multi-Model Timestamp Ensembling
语音识别 | 7.2/10