[Paper 리뷰] Wav2Vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
Wav2Vec 2.0: A Framework for Self-Supervised Learning of Speech RepresentationsSpeech audio만으로 powerful representation을 학습하고 transcribed speech에 대한 fine-tuning을 통해 speech recognition 성능을 향상할 수 있음Wav2Vec 2.0Latent space에서 speech input을 maskJointly learned latent representation의 quantization에 대한 contrastive task를 solve'논문 (NeurIPS 2020) : Paper Link1. IntroductionSpeech recognition에서 labeled data는..
[Paper 리뷰] Wav2Vec: Unsupervised Pre-Training for Speech Recognition
Wav2Vec: Unsupervised Pre-Training for Speech RecognitionRaw audio representation을 학습하여 speech recognition에 unsupervised pre-training을 도입할 수 있음Wav2VecUnlabeled audio data를 기반으로 training 하고, resulting representation을 acoustic model training을 개선하는 데 사용Noise contrastive binary classification을 통해 simple multi-layer convolutional neural network를 optimize논문 (INTERSPEECH 2019) : Paper Link1. Introducti..
[Paper 리뷰] Speech2Vec: A Sequence-to-Sequence Framework for Learning Word Embeddings from Speech
Speech2Vec: A Sequence-to-Sequence Framework for Learning Word Embeddings from SpeechSpeech corpus로부터 얻어진 audio segment의 fixed-length vector representation을 학습하여 semantic information을 얻을 수 있음Speech2VecRNN encoder-decoder framework를 기반으로 semantically simillar 한 embedding을 얻음Training을 위해 Skipgrams, Continuous Bag-of-Words를 활용논문 (INTERSPEECH 2018) : Paper Link1. IntroductionNatural Language Process..