Skip to main content
Search

# CTC acoustic model

1 related articles

Subscribe to updates
  1. arXiv

    Frozen CTC acoustic and language models plus a test-time adaptation module let ASR learn new words from unlabeled test data, cutting recurring-OOV character error rate by up to 14.97% relative on LibriSpeech

    The work proposes giving automatic speech recognition the ability to learn the contextual representations and spellings of new words from unlabeled test data at test time: a frozen CTC acoustic model provides spellings, a frozen language model provides contextual evidence for out-of-vocabulary (OOV) word detection, and an adaptation module expands the vocabulary by learning lexical token representations with distributions over CTC-generated candidates, optimized by minimizing a Kullback-Leibler divergence (KLD) objective; the authors further argue that the CTC-weighted language model log likelihood ratio can be interpreted as the KLD between the unknown correct ASR and the unsupervised learned ASR, and that via a Pinsker bound the square root of KLD can be interpreted as an upper bound on

You’re all caught up