https://github.com/mct10/repcodec
공식 코드RepCodec: A Speech Representation Codec for Speech Tokenization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
RepCodec: A Speech Representation Codec for Speech Tokenization
PromptCBLUE: A Chinese Prompt Tuning Benchmark for the Medical Domain
DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization
Contrastive Learning for Improving ASR Robustness in Spoken Language Understanding
FlowQA: Grasping Flow in History for Conversational Machine Comprehension
Leveraging Cross-Lingual Transfer Learning in Spoken Named Entity Recognition Systems
SlotRefine: A Fast Non-Autoregressive Model for Joint Intent Detection and Slot Filling
TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling
DM-Codec: Distilling Multimodal Representations for Speech Tokenization
AfriHuBERT: A self-supervised speech representation model for African languages
Exploring the Limits of Natural Language Inference Based Setup for Few-Shot Intent Detection
Confusion2vec 2.0: Enriching Ambiguous Spoken Language Representations with Subwords
Triplet Entropy Loss: Improving The Generalisation of Short Speech Language Identification Systems
Self-Supervised Syllable Discovery Based on Speaker-Disentangled HuBERT
Large Language Models for Expansion of Spoken Language Understanding Systems to New Languages
Spoken Language Identification System for English-Mandarin Code-Switching Child-Directed Speech
Hierarchical Dialogue Understanding with Special Tokens and Turn-level Attention
Leveraging Machine-Generated Rationales to Facilitate Social Meaning Detection in Conversations
ProsocialDialog: A Prosocial Backbone for Conversational Agents
Timers and Such: A Practical Benchmark for Spoken Language Understanding with Numbers
Timers and Such: A Practical Benchmark for Spoken Language Understanding with Numbers
DialoGen: Generalized Long-Range Context Representation for Dialogue Systems
Contrastive and Consistency Learning for Neural Noisy-Channel Model in Spoken Language Understanding
Data Augmentation with Atomic Templates for Spoken Language Understanding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.