Sign in
Loss Masking Is Not Needed in Decoder-only Transformer for Discrete-token Based ASR.
Qian Chen
Wen Wang
Qinglin Zhang
Siqi Zheng
Shiliang Zhang
Chong Deng
Yukun Ma
Hai Yu
Jiaqing Liu
Chong Zhang
Published in:
CoRR (2023)
Keyphrases
</>
automatic speech recognition
information loss
low complexity
error concealment
fuzzy logic
discrete geometry
hidden markov models
error rate
power system
speech recognition
human visual system
discrete space
fpga implementation