# Investigating the Effect of Label Topology and Training Criterion on ASR Performance and Alignment Quality

arXiv: https://arxiv.org/abs/2407.11641 · HTML: https://mlsanity.com/paper/2407.11641/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jul 2024.

## Built on by (most cited first, 3 of 3)

- [The Conformer Encoder May Reverse the Time Dimension](https://mlsanity.com/paper/2410.00680/) (2024)
- [A Native-Reference Coordinate Geometry for L2 Pronunciation Deviation Using Self-Supervised Speech Models](https://mlsanity.com/paper/2609.28060/) (2026)
- [A Native-Reference Phone-Class Geometry for Second-Language Pronunciation Analysis](https://mlsanity.com/paper/2609.30075/) (2026)

## Abstract (arXiv)

The ongoing research scenario for automatic speech recognition (ASR) envisions a clear division between end-to-end approaches and classic modular systems. Even though a high-level comparison between the two approaches in terms of their requirements and (dis)advantages is commonly addressed, a closer comparison under similar conditions is not readily available in the literature. In this work, we present a comparison focused on the label topology and training criterion. We compare two discriminative alignment models with hidden Markov model (HMM) and connectionist temporal classification topology, and two first-order label context ASR models utilizing factored HMM and strictly monotonic recurrent neural network transducer, respectively. We use different measurements for the evaluation of the alignment quality, and compare word error rate and real time factor of our best systems. Experiments are conducted on the LibriSpeech 960h and Switchboard 300h tasks.