AppTek Call-Center Dialogues: A Multi-Accent Long-Form Benchmark for English ASR

TL;DR

This paper introduces the AppTek Call-Center Dialogues corpus, a diverse, spontaneous English speech dataset with multiple accents, designed for evaluating ASR robustness in conversational AI.

Contribution

The work provides a new, comprehensive benchmark dataset for English ASR across multiple accents and scenarios, addressing limitations of existing corpora.

Findings

ASR performance varies significantly across accents.

Segmentation approaches impact ASR accuracy.

General American English benchmarks do not ensure robustness for other accents.

Abstract

Evaluating English ASR systems for conversational AI applications remains difficult, as many publicly available corpora are either pre-segmented into short segments, consist of read or prepared speech, or lack explicit dialect annotations to evaluate robustness for a diverse user base. This work presents the AppTek Call-Center Dialogues corpus, a collection of spontaneous, role-played agent-customer conversations spanning fourteen English accents covering sixteen service-oriented scenarios. The dataset was commissioned specifically for evaluation and none of the audio or text was publicly available prior to release, reducing the risk of overlap with existing large-scale pretraining corpora. We benchmark a set of open-source ASR systems under different segmentation approaches. Results show substantial variation across accents and segmentation methods, indicating that good performance on general American English benchmarks does not necessarily generalize to other accents.