https://github.com/dyunis/spectral_dynamics
공식 코드Approaching Deep Learning through the Spectral Dynamics of Weights
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/edresson/wav2vec-wrapper
공식 코드https://github.com/edunlp/nemo-multistage-classroom-diarization
공식 코드https://github.com/efeslab/liteasr
공식 코드LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation
https://github.com/ehughson/voice_toolbox
공식 코드Read the Room: Adapting a Robot's Voice to Ambient and Social Contexts
https://github.com/emirdemirel/ALTA
공식 코드https://github.com/emirdemirel/AutomaticLyricsTranscription-with-Self-Attention
공식 코드Automatic Lyrics Transcription using Dilated Convolutional Neural Networks with Self-Attention
https://github.com/emonosuke/emoasr
공식 코드Non-autoregressive Error Correction for CTC-based ASR with Phone-conditioned Masked LM
https://github.com/emrys365/se-scaling
공식 코드Beyond Performance Plateaus: A Comprehensive Study on Scalability in Speech Enhancement
https://github.com/enesyugan/pier-codeswitching-evaluation
공식 코드PIER: A Novel Metric for Evaluating What Matters in Code-Switching
https://github.com/ericguizzo/anti_transfer
공식 코드Anti-Transfer Learning for Task Invariance in Convolutional Neural Networks for Speech Processing
https://github.com/esalesky/xnmt-devel
공식 코드https://github.com/espnet/espnet
공식 코드https://github.com/espnet/espnet/tree/master/egs/chime6/asr1
공식 코드Towards a Competitive End-to-End Speech Recognition for CHiME-6 Dinner Party Transcription
https://github.com/espnet/espnet/tree/master/egs/mgb2/asr1
공식 코드Arabic Speech Recognition by End-to-End, Modular Systems and Human
https://github.com/espnet/espnet/tree/master/egs2/qasr_tts/tts1
공식 코드Unsupervised Data Selection for TTS: Using Arabic Broadcast News as a Case Study
https://github.com/esyoon7/litta
공식 코드LI-TTA: Language Informed Test-Time Adaptation for Automatic Speech Recognition
https://github.com/ewaldvdw/kaldi/tree/mbnf_cs2020/egs/nchlt_multi_bnfs/s5
공식 코드https://github.com/exgc/avmust-ted
공식 코드https://github.com/exgc/opensr
공식 코드OpenSR: Open-Modality Speech Recognition via Maintaining Multi-Modality Alignment
https://github.com/explainableml/zeraucap
공식 코드Zero-shot audio captioning with audio-language model guidance and audio context keywords
https://github.com/f90/jamendolyrics
공식 코드Contrastive Learning-Based Audio to Lyrics Alignment for Multiple Languages
https://github.com/facebookresearch/CPC_audio
공식 코드https://github.com/facebookresearch/av_hubert
공식 코드https://github.com/facebookresearch/covost
공식 코드CoVoST 2 and Massively Multilingual Speech-to-Text Translation
https://github.com/facebookresearch/emg2qwerty
공식 코드emg2qwerty: A Large Dataset with Baselines for Touch Typing using Surface Electromyography
https://github.com/facebookresearch/fairseq
공식 코드https://github.com/facebookresearch/fairseq/tree/main/examples/data2vec
공식 코드https://github.com/facebookresearch/gtn_applications/blob/main/criterions/stc.py
공식 코드Star Temporal Classification: Sequence Classification with Partially Labeled Data
https://github.com/facebookresearch/learning-audio-visual-dereverberation
공식 코드https://github.com/facebookresearch/libri-light
공식 코드Libri-Light: A Benchmark for ASR with Limited or No Supervision
https://github.com/facebookresearch/muavic
공식 코드https://github.com/facebookresearch/rlr-audio-propagation
공식 코드SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning
https://github.com/facebookresearch/seamless_communication
공식 코드SeamlessM4T: Massively Multilingual & Multimodal Machine Translation
https://github.com/facebookresearch/sound-spaces
공식 코드SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning
https://github.com/facebookresearch/stopes
공식 코드BLASER: A Text-Free Speech-to-Speech Translation Evaluation Metric
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.