Principled Comparisons for End-to-End Speech Recognition: Attention vs Hybrid at the 1000-hour Scale

Loading...
Thumbnail Image

Access rights

openAccess
publishedVersion

URL

Journal Title

Journal ISSN

Volume Title

A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä

Date

2024

Major/Subject

Mcode

Degree programme

Language

en

Pages

16

Series

IEEE/ACM Transactions on Audio, Speech, and Language Processing, Volume 32, pp. 623-638

Abstract

End-to-End speech recognition has become the center of attention for speech recognition research, but Hybrid Hidden Markov Model Deep Neural Network (HMM/DNN) -systems remain a competitive approach in terms of performance. End-to-End models may be better at very large data scales, and HMM / DNN-systems may have an advantage in low-resource scenarios, but the thousand-hour scale is particularly interesting for comparisons. At that scale experiments have not been able to conclusively demonstrate which approach is best, or if the heterogeneous approaches yield similar results. In this work, we work towards answering that question for Attention-based Encoder-Decoder models compared with HMM / DNN-systems. We present two simple experimental design principles, and how to build systems adhering to those principles. We demonstrate how those principles remove confounding variables related to both data, and neural architecture and training. We apply the principles in a set of experiments on three diverse thousand-hour-scale tasks. In our experiments, the HMM / DNN-systems yield equal or better results in almost all cases.

Description

Keywords

ASR, HMM/DNN, End-to-End

Other note

Citation

Rouhe, A, Grósz, T & Kurimo, M 2024, ' Principled Comparisons for End-to-End Speech Recognition: Attention vs Hybrid at the 1000-hour Scale ', IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 32, pp. 623-638 . https://doi.org/10.1109/taslp.2023.3336517