HuBERT

GPTKB entity

Statements (41)
Predicate Object
gptkbp:instanceOf speech representation learning model
gptkbp:architecture gptkb:transformation
gptkbp:arXivID 2106.07447
gptkbp:author gptkb:Abdelrahman_Mohamed
gptkb:Alexei_Baevski
gptkb:Ruslan_Salakhutdinov
gptkb:James_Glass
gptkb:Wei-Ning_Hsu
Benjamin Bolte
Kuan-Chieh Wang
Yao-Hung Hubert Tsai
gptkbp:basedOn self-supervised learning
gptkbp:citation HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units
gptkbp:developedBy gptkb:Facebook_AI_Research
gptkbp:evaluationBenchmark gptkb:LibriSpeech
gptkb:TIMIT
CommonVoice
gptkbp:format feature vectors
waveform
gptkbp:fullName Hidden-Unit BERT
https://www.w3.org/2000/01/rdf-schema#label HuBERT
gptkbp:input raw audio
gptkbp:language English
gptkbp:license gptkb:MIT
gptkbp:memiliki_tugas automatic speech recognition
unsupervised speech representation learning
gptkbp:openSource yes
gptkbp:pretrainingData gptkb:Libri-Light
gptkb:LibriSpeech
gptkbp:pretrainingMethod masked prediction
gptkbp:publishedIn 2021
gptkbp:relatedTo gptkb:wav2vec_2.0
gptkb:BERT
gptkbp:repository https://github.com/pytorch/fairseq/tree/main/examples/hubert
gptkbp:usedFor speech recognition
speech representation
gptkbp:bfsParent gptkb:pre-trained_WavLM_models
gptkb:pre-trained_wav2vec2_models
gptkb:Hugging_Face_models
gptkb:Wei-Ning_Hsu
gptkbp:bfsLayer 7