Multilingual and Fully Non-Autoregressive ASR with Large Language Model Fusion: A Comprehensive Study

Built on

R. Zazo Candil, T. N. Sainath, G. Simko, and C. Parada, “Feature learning with raw-waveform cldnns for voice activity detection,”
2016
Earlier work this paper cites.
H. Soltau, H. Liao, and H. Sak, “Reducing the Computational Complexity for Whole Word Models,” in
2017
Earlier work this paper cites.
J. Devlin, M. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,”
Original
2018
Earlier work this paper cites.
A. Kannan
2018
Earlier work this paper cites.
M. Shoeybi
Original
2019
Earlier work this paper cites.
C.-C. Chiu, W. Han, Y. Zhang
2019
Earlier work this paper cites.
V. Pratap
2020
Earlier work this paper cites.
T. Brown
2020
Earlier work this paper cites.

J. Salazar, D. Liang, T. Q. Nguyen, and K. Kirchhoff, “Masked language model scoring,” in
2020
Cited alongside, same era.
C. Raffel
2020
Cited alongside, same era.
A. Gulati
2020
Cited alongside, same era.
C.-C. Chiu
2021
Cited alongside, same era.
Y. Zhang
2022
Cited alongside, same era.
A. Chowdhery
Original
2022
Cited alongside, same era.
F.-H. Yu, K.-Y. Chen, and K.-H. Lu, “Non-autoregressive asr modeling using pre-trained language models for chinese speech recognition,”
2022

A. Radford
2023
Later among the works it cites.
H. Touvron
Original
2023
Later among the works it cites.
Y. Zhang
Original
2023
Later among the works it cites.
Y. Li, Y. Wu, J. Li, and S. Liu, “Prompting large language models for zero-shot domain adaptation in speech recognition,”
Original
2023
Later among the works it cites.
A. Conneau
2023
Later among the works it cites.
S. Bubeck
Original
2023