# HMM vs. CTC for Automatic Speech Recognition: Comparison Based on Full-Sum Training from Scratch

arXiv: https://arxiv.org/abs/2210.09951 · HTML: https://mlsanity.com/paper/2210.09951/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Oct 2022.

## Built on by (most cited first, 4 of 4)

- [End-to-End Speech Recognition: A Survey](https://mlsanity.com/paper/2303.03329/) (2023)
- [RASR2: The RWTH ASR Toolkit for Generic Sequence-to-sequence Speech Recognition](https://mlsanity.com/paper/2305.17782/) (2023)
- [The Conformer Encoder May Reverse the Time Dimension](https://mlsanity.com/paper/2410.00680/) (2024)
- [End-to-End Training of a Neural HMM with Label and Transition Probabilities](https://mlsanity.com/paper/2310.02724/) (2023)

## Abstract (arXiv)

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.