1.9k citations · 2.9k across the 17 of their papers we have counts for
4 papers · 1 filter
TESSP: Text-Enhanced Self-Supervised Speech Pre-training
Zhuoyuan Yao, Shuo Ren, Sanyuan Chen +3
Self-supervised speech pre-training empowers the model with the contextual structure inherent in the speech signal while self-supervised text pre-training empowers the model with l…
RAPO: An Adaptive Ranking Paradigm for Bilingual Lexicon Induction
Zhoujin Tian, Chaozhuo Li, Shuo Ren +8
Bilingual lexicon induction induces the word translations by aligning independently trained word embeddings in two languages. Existing approaches generally focus on minimizing the…
SpeechLM: Enhanced Speech Pre-Training with Unpaired Textual Data
Ziqiang Zhang, Sanyuan Chen, Long Zhou +8
How to boost speech pre-training with textual data is an unsolved problem due to the fact that speech and text are very different modalities with distinct characteristics. In this…
Speech Pre-training with Acoustic Piece
Shuo Ren, Shujie Liu, Yu Wu +2
Previous speech pre-training methods, such as wav2vec2.0 and HuBERT, pre-train a Transformer encoder to learn deep representations from audio data, with objectives predicting eithe…