2 papers
cs.CL2023
N-gram Boosting: Improving Contextual Biasing with Normalized N-gram Targets
Wang Yau Li, Shreekantha Nadig, Karol Chang +5
Accurate transcription of proper names and technical terms is particularly important in speech-to-text applications for business conversations. These words, which are essential to…
cs.SD2021
Comparison of SVD and factorized TDNN approaches for speech to text
Jeffrey Josanne Michael, Nagendra Kumar Goel, Navneeth K +2
This work concentrates on reducing the RTF and word error rate of a hybrid HMM-DNN. Our baseline system uses an architecture with TDNN and LSTM layers. We find this architecture pa…