https://github.com/mbzuai-nlp/audiojailbreak
공식 코드Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language 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/mbzuai-nlp/mixat
공식 코드https://github.com/mbzuai-nlp/sttatts
공식 코드https://github.com/mdhk/ssl-nl-eval
공식 코드https://github.com/mdoumbouya/nicolingua
공식 코드https://github.com/mechanicalsea/lighthubert
공식 코드https://github.com/medbar/kaldi/tree/ltlm/egs/librispeech/s5/fairseq_ltlm
공식 코드LT-LM: a novel non-autoregressive language model for single-shot lattice rescoring
https://github.com/mehdi-mirzapour/emotional_speech_recognition
공식 코드Emotional Speech Recognition with Pre-trained Deep Visual Models
https://github.com/menloresearch/ichigo
공식 코드Speechless: Speech Instruction Training Without Speech for Low Resource Languages
https://github.com/merlresearch/tssep
공식 코드TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings
https://github.com/mgaido91/FBK-fairseq-ST
공식 코드https://github.com/miamoto/conformer-ntm
공식 코드Memory-augmented conformer for improved end-to-end long-form ASR
https://github.com/microsoft/AEC-Challenge
공식 코드https://github.com/microsoft/NeuralSpeech
공식 코드FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition
https://github.com/microsoft/msrflute
공식 코드FLUTE: A Scalable, Extensible Framework for High-Performance Federated Learning Simulations
https://github.com/microsoft/speecht5
공식 코드SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing
https://github.com/microsoft/unilm
공식 코드WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
https://github.com/microsoft/unilm/tree/master/LatentLM
공식 코드Multimodal Latent Language Modeling with Next-Token Diffusion
https://github.com/microsoft/unispeech
공식 코드UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training
https://github.com/mict-zhaw/chall_e2e_stt
공식 코드Error-preserving Automatic Speech Recognition of Young English Learners' Language
https://github.com/midas-research/DECA
공식 코드Harnessing GANs for Zero-shot Learning of New Classes in Visual Speech Recognition
https://github.com/midas-research/audino
공식 코드https://github.com/mikewangwzhl/vidil
공식 코드Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners
https://github.com/milaniusz/speech2brain2speech
공식 코드Towards Decoding Brain Activity During Passive Listening of Speech
https://github.com/mindslab-ai/assem-vc
공식 코드Assem-VC: Realistic Voice Conversion by Assembling Modern Speech Synthesis Techniques
https://github.com/mindslab-ai/phaseaug
공식 코드PhaseAug: A Differentiable Augmentation for Speech Synthesis to Simulate One-to-Many Mapping
https://github.com/ming024/FastSpeech2
공식 코드Hierarchical Prosody Modeling for Non-Autoregressive Speech Synthesis
https://github.com/mingjund/mapudungun-corpus
공식 코드https://github.com/minglunhan/cif-coldec
공식 코드Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge Selection
https://github.com/mininglamp-technology/asr-blockformer
공식 코드Improving Mandarin Speech Recogntion with Block-augmented Transformer
https://github.com/minkjung/blankcollapse
공식 코드Blank Collapse: Compressing CTC emission for the faster decoding
https://github.com/miosipof/lie-dasr
공식 코드Dysarthria Normalization via Local Lie Group Transformations for Robust ASR
https://github.com/mispchallenge/misp-icme-avsr
공식 코드https://github.com/mit-ccc/RadioTalk
공식 코드https://github.com/mkt-dataoceanai/cnvsrc2023baseline
공식 코드The NPU-ASLP-LiAuto System Description for Visual Speech Recognition in CNVSRC 2023
https://github.com/mlspeech/whisperdenoiser
공식 코드Enhanced ASR Robustness to Packet Loss with a Front-End Adaptation Network
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.