https://github.com/yuchen005/star-adapt
공식 코드Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models
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/yuchen005/univpm
공식 코드https://github.com/yueen-ma/awesome-vla
공식 코드https://github.com/yuhangear/multi-modal-learning
공식 코드Speech-text based multi-modal training with bidirectional attention for improved speech recognition
https://github.com/yujxx/podagent
공식 코드https://github.com/yunyikristy/skipNet
공식 코드Unpaired Image-to-Speech Synthesis with Multimodal Information Bottleneck
https://github.com/yuriak/SpeechDialogueFactory
공식 코드https://github.com/yuwchen/baspro
공식 코드BASPRO: a balanced script producer for speech corpus collection based on the genetic algorithm
https://github.com/yygle/HybridFormer
공식 코드HYBRIDFORMER: improving SqueezeFormer with hybrid attention and NSR mechanism
https://github.com/yygle/LMLA
공식 코드LMEC: Learnable Multiplicative Absolute Position Embedding Based Conformer for Speech Recognition
https://github.com/zabir-nabil/bangla-tts
공식 코드https://github.com/zaharah/ood_audio
공식 코드On Out-of-Distribution Detection for Audio with Deep Nearest Neighbors
https://github.com/zbang/usef-tse
공식 코드USEF-TSE: Universal Speaker Embedding Free Target Speaker Extraction
https://github.com/zelokuo/VPIDM
공식 코드https://github.com/zengzp0912/SEAME-dev-set
공식 코드On the End-to-End Solution to Mandarin-English Code-switching Speech Recognition
https://github.com/zexupan/avse_hybrid_loss
공식 코드A Hybrid Continuity Loss to Reduce Over-Suppression for Time-domain Target Speaker Extraction
https://github.com/zexupan/imaginenet
공식 코드ImagineNET: Target Speaker Extraction with Intermittent Visual Cue through Embedding Inpainting
https://github.com/zexupan/reentry
공식 코드https://github.com/zhang-wy15/Attack_practical_asv
공식 코드Attack on practical speaker verification system using universal adversarial perturbations
https://github.com/zhangxiaozao/BO-Aug
공식 코드Learning Optimal Data Augmentation Policies via Bayesian Optimization for Image Classification Tasks
https://github.com/zhenye234/CoMoSpeech
공식 코드CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model
https://github.com/zhenye234/LLaSA_training
공식 코드Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis
https://github.com/zhenye234/xcodec
공식 코드Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model
https://github.com/zhenzi-weng/deepsc-st_demonstration
공식 코드Deep Learning Enabled Semantic Communications with Speech Recognition and Synthesis
https://github.com/zhu-han/ASR-Adaption-Class-Similarity
공식 코드Domain Adaptation Using Class Similarity for Robust Speech Recognition
https://github.com/zhu-han/castle
공식 코드Boosting Cross-Domain Speech Recognition with Self-Supervision
https://github.com/zhuole1025/LyricWhiz
공식 코드LyricWhiz: Robust Multilingual Zero-shot Lyrics Transcription by Whispering to ChatGPT
https://github.com/zinengtang/tvlt
공식 코드https://github.com/znlp/zero-shot-st
공식 코드Discrete Cross-Modal Alignment Enables Zero-Shot Speech Translation
https://github.com/zoe-ca/deepgd
공식 코드DeepGD: A Multi-Objective Black-Box Test Selection Approach for Deep Neural Networks
https://github.com/zombbie/entity-synthetic-dataset
공식 코드Towards Contextual Spelling Correction for Customization of End-to-end Speech Recognition Systems
https://github.com/zorikg/red-ace
공식 코드RED-ACE: Robust Error Detection for ASR using Confidence Embeddings
https://github.com/zpforlove/rene
공식 코드Rene: A Pre-trained Multi-modal Architecture for Auscultation of Respiratory Diseases
https://github.com/zqs01/data2vecnoisy
공식 코드https://github.com/zqs01/multi-channel-wav2vec2
공식 코드Multichannel AV-wav2vec2: A Framework for Learning Multichannel Multi-Modal Speech Representation
https://github.com/zslin177/copyne
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.