# TRScore: A Novel GPT-based Readability Scorer for ASR Segmentation and Punctuation model evaluation and selection

arXiv: https://arxiv.org/abs/2210.15104 · HTML: https://mlsanity.com/paper/2210.15104/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 19 references that are in the map.
- First posted on arXiv 27 Oct 2022.

## Builds on (most cited first, 11 of 11)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model](https://mlsanity.com/paper/2201.11990/) (2022)
- [MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance](https://mlsanity.com/paper/1909.02622/) (2019)
- [Evaluating User Perception of Speech Recognition System Quality with Semantic Distance Metric](https://mlsanity.com/paper/2110.05376/) (2021)
- [Streaming Punctuation for Long-form Dictation with Transformers](https://mlsanity.com/paper/2210.05756/) (2022)
- [Smart Speech Segmentation using Acousto-Linguistic Features with look-ahead](https://mlsanity.com/paper/2210.14446/) (2022)

## Built on by (most cited first, 1 of 1)

- [Call2Instruct: Automated Pipeline for Generating Q&A Datasets from Call Center Recordings for LLM Fine-Tuning](https://mlsanity.com/paper/2601.14263/) (2025)

## Abstract (arXiv)

Punctuation and Segmentation are key to readability in Automatic Speech Recognition (ASR), often evaluated using F1 scores that require high-quality human transcripts and do not reflect readability well. Human evaluation is expensive, time-consuming, and suffers from large inter-observer variability, especially in conversational speech devoid of strict grammatical structures. Large pre-trained models capture a notion of grammatical structure. We present TRScore, a novel readability measure using the GPT model to evaluate different segmentation and punctuation systems. We validate our approach with human experts. Additionally, our approach enables quantitative assessment of text post-processing techniques such as capitalization, inverse text normalization (ITN), and disfluency on overall readability, which traditional word error rate (WER) and slot error rate (SER) metrics fail to capture. TRScore is strongly correlated to traditional F1 and human readability scores, with Pearson's correlation coefficients of 0.67 and 0.98, respectively. It also eliminates the need for human transcriptions for model selection.