Login / Signup
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:
ICASSP (2024)
Keyphrases
</>
information loss
fuzzy logic
automatic speech recognition
low complexity
power system
speech recognition
fault diagnosis
video codec
motion estimation
finite number
error propagation
discrete geometry
spontaneous speech
discrete version
noisy channel