Papers with Code 아카이브
Speech Recognition
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 11
- 평가표
- 236
- 보존된 평가 기록
- 398
Speech Recognition is the task of converting spoken language into text. It involves recognizing the words spoken in an audio recording and transcribing them into a written format. The goal is to accurately transcribe the speech in real-time or from recorded audio, taking into account factors such as accents, speaking speed, and background noise.
<span style="color:grey; opacity: 0.6">( Image credit: SpecAugment )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/xinjli/allosaurus
공식 코드Universal Phone Recognition with a Multilingual Allophone System
https://github.com/xinjli/asr2k
공식 코드ASR2K: Speech Recognition for Around 2000 Languages without Audio
https://github.com/xiph/lpcnet
공식 코드Neural Speech Synthesis on a Shoestring: Improving the Efficiency of LPCNet
https://github.com/xllyu-nlp/docia
공식 코드DoCIA: An Online Document-Level Context Incorporation Agent for Speech Translation
https://github.com/xuchenglin28/speaker_extraction
공식 코드Target Speaker Verification with Selective Auditory Attention for Single and Multi-talker Speech
https://github.com/xuchennlp/s2t
공식 코드https://github.com/y0ngjaenius/cvpr2024_flowerformer
공식 코드FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformer
https://github.com/yairl/ivrit.ai
공식 코드ivrit.ai: A Comprehensive Dataset of Hebrew Speech for AI Research and Development
https://github.com/yajiemiao/eesen
공식 코드EESEN: End-to-End Speech Recognition using Deep RNN Models and WFST-based Decoding
https://github.com/yan-gao-GY/Flower-SpeechBrain
공식 코드End-to-End Speech Recognition from Federated Acoustic Models
https://github.com/yan-gao-GY/Muti-teacherKD
공식 코드https://github.com/yandex-research/distill-nf
공식 코드https://github.com/yandex-research/msr
공식 코드https://github.com/yanghaha0908/fasthubert
공식 코드Fast-HuBERT: An Efficient Training Framework for Self-Supervised Speech Representation Learning
https://github.com/yangjingyuan/constdecoder
공식 코드ASR Error Correction with Constrained Decoding on Operation Prediction
https://github.com/yaoming95/unipunc
공식 코드Unified Multimodal Punctuation Restoration Framework for Mixed-Modality Corpus
https://github.com/yaq007/cleverhans/tree/master/examples/adversarial_asr
공식 코드Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition
https://github.com/yasserdahouml/vsr_test_set
공식 코드https://github.com/yc-li20/SER-on-WER-and-Fusion
공식 코드https://github.com/yc-li20/emotion-prompt
공식 코드https://github.com/yc-li20/semi-supervised-training
공식 코드Semi-Supervised Cognitive State Classification from Speech with Multi-View Pseudo-Labeling
https://github.com/yc9701/pansori-tedxkr-corpus
공식 코드Pansori: ASR Corpus Generation from Open Online Video Contents
https://github.com/yctam/dstc10_track2_task2
공식 코드Robust Unstructured Knowledge Access in Conversational Dialogue with ASR Errors
https://github.com/yeonseokjeong/judge-specialist
공식 코드https://github.com/yl4579/HiFTNet
공식 코드https://github.com/yl4579/StyleTTS
공식 코드StyleTTS: A Style-Based Generative Model for Natural and Diverse Text-to-Speech Synthesis
https://github.com/yonatankarimish/YonaVox
공식 코드https://github.com/yosukehiguchi/espnet
공식 코드Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units
https://github.com/youngeun1209/neurotalk
공식 코드Towards Voice Reconstruction from EEG during Imagined Speech
https://github.com/ytf-philp/self-powered-lsm
공식 코드Self-Powered LLM Modality Expansion for Large Speech-Text Models
https://github.com/yuchen005/dpsl-asr
공식 코드Interactive Feature Fusion for End-to-End Noise-Robust Speech Recognition
https://github.com/yuchen005/gila
공식 코드Cross-Modal Global Interaction and Local Alignment for Audio-Visual Speech Recognition
https://github.com/yuchen005/gradient-remedy
공식 코드Gradient Remedy for Multi-Task Learning in End-to-End Noise-Robust Speech Recognition
https://github.com/yuchen005/mir-gan
공식 코드https://github.com/yuchen005/robustger
공식 코드Large Language Models are Efficient Learners of Noise-Robust Speech Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.