# ASR Performance Prediction on Unseen Broadcast Programs using Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1804.08477 · HTML: https://mlsanity.com/paper/1804.08477/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Apr 2018.

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

- [WER-BERT: Automatic WER Estimation with BERT in a Balanced Ordinal Classification Paradigm](https://mlsanity.com/paper/2101.05478/) (2021)
- [DaLC: Domain Adaptation Learning Curve Prediction for Neural Machine Translation](https://mlsanity.com/paper/2204.09259/) (2022)
- [On the Robust Approximation of ASR Metrics](https://mlsanity.com/paper/2502.12408/) (2025)

## Abstract (arXiv)

In this paper, we address a relatively new task: prediction of ASR performance on unseen broadcast programs. We first propose an heterogenous French corpus dedicated to this task. Two prediction approaches are compared: a state-of-the-art performance prediction based on regression (engineered features) and a new strategy based on convolutional neural networks (learnt features). We particularly focus on the combination of both textual (ASR transcription) and signal inputs. While the joint use of textual and signal features did not work for the regression baseline, the combination of inputs for CNNs leads to the best WER prediction performance. We also show that our CNN prediction remarkably predicts the WER distribution on a collection of speech recordings.