HMM vs. CTC for Automatic Speech Recognition: Comparison Based on Full-Sum Training from Scratch
IEEE Spoken Language Technology Workshop (SLT), pp. 287–294
Abstract
In this work, we compare from-scratch sequence-level cross-entropy (full-sum) training of Hidden Markov Model (HMM) and Connectionist Temporal Classification (CTC) topologies for automatic speech recognition (ASR). Besides accuracy, we further analyze their capability for generating high-quality time alignment between the speech signal and the transcription, which can be crucial for many subsequent applications. Moreover, we propose several methods to improve convergence of from-scratch full-sum training by addressing the alignment modeling issue. Systematic comparison is conducted on both Switchboard and LibriSpeech corpora across CTC, posterior HMM with and w/o transition probabilities, and standard hybrid HMM. We also provide a detailed analysis of both Viterbi forced-alignment and Baum-Welch full-sum occupation probabilities.
Authors 5
-
Affiliation as printed
RWTH Aachen University,Human Language Technology and Pattern Recognition Group,Germany
Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Germany
-
Affiliation as printed
RWTH Aachen University,Human Language Technology and Pattern Recognition Group,Germany
AppTek GmbH, Aachen, Germany
Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Germany
-
Affiliation as printed
RWTH Aachen University,Human Language Technology and Pattern Recognition Group,Germany
AppTek GmbH, Aachen, Germany
Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Germany
-
Affiliation as printed
RWTH Aachen University,Human Language Technology and Pattern Recognition Group,Germany
AppTek GmbH, Aachen, Germany
Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Germany
-
Affiliation as printed
RWTH Aachen University,Human Language Technology and Pattern Recognition Group,Germany
AppTek GmbH, Aachen, Germany
Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Germany
Cited by 12 stored of 12
12 results
No patents citing this paper on Lens.org (checked 2026-10-06).