https://github.com/kathania/Interspeech-2020-Non-native-children-ASR
공식 코드Data augmentation using prosody and false starts to recognize non-native children's speech
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Data augmentation using prosody and false starts to recognize non-native children's speech
ChamaleonLLM: Batch-Aware Dynamic Low-Rank Adaptation via Inference-Time Clusters
Counterfactual Language Model Adaptation for Suggesting Phrases
Video Enriched Retrieval Augmented Generation Using Aligned Video Captions
Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answering
A context-aware knowledge transferring strategy for CTC-based ASR
Period-LLM: Extending the Periodic Capability of Multimodal Large Language Model
LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Model
Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization
Scaling Expert Language Models with Unsupervised Domain Discovery
DEMix Layers: Disentangling Domains for Modular Language Modeling
DEMix Layers: Disentangling Domains for Modular Language Modeling
The Importance of Being Recurrent for Modeling Hierarchical Structure
Efficient recurrent architectures through activity sparsity and sparse back-propagation through time
Debiasing the Cloze Task in Sequential Recommendation with Bidirectional Transformers
DuplexMamba: Enhancing Real-time Speech Conversations with Duplex and Streaming Capabilities
ArNLI: Arabic Natural Language Inference for Entailment and Contradiction Detection
MedRep: Medical Concept Representation for General Electronic Health Record Foundation Models
Automatic Short Math Answer Grading via In-context Meta-learning
Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
Riemannian Normalizing Flow on Variational Wasserstein Autoencoder for Text Modeling
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.