Projects per year
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.
Original language | English |
---|---|
Pages (from-to) | 623-638 |
Number of pages | 16 |
Journal | IEEE/ACM Transactions on Audio, Speech, and Language Processing |
Volume | 32 |
Early online date | 24 Nov 2023 |
DOIs | |
Publication status | Published - 2024 |
MoE publication type | A1 Journal article-refereed |
Keywords
- ASR
- HMM/DNN
- End-to-End
Fingerprint
Dive into the research topics of 'Principled Comparisons for End-to-End Speech Recognition: Attention vs Hybrid at the 1000-hour Scale'. Together they form a unique fingerprint.Projects
- 2 Active
-
LAREINA: LAREINA - Language Resource Infrastructure for AI
Kurimo, M. (Principal investigator), Moisio, A. (Project Member), Getman, Y. (Project Member), Porjazovski, D. (Project Member), Rouhe, A. (Project Member) & Virkkunen, A. (Project Member)
01/01/2023 → 31/12/2025
Project: Business Finland: Strategic centres for science, technology and innovation (SHOK)
-
USSEE: Understanding Speech and Scene with Ears and Eyes
Kurimo, M. (Principal investigator), Virkkunen, A. (Project Member) & Grósz, T. (Project Member)
01/01/2022 → 31/12/2024
Project: Academy of Finland: Other research funding