arXiv Open Access 2025

On Barriers to Archival Audio Processing

Peter Sullivan Muhammad Abdul-Mageed

Lihat Sumber

Abstrak

In this study, we leverage a unique UNESCO collection of mid-20th century radio recordings to probe the robustness of modern off-the-shelf language identification (LID) and speaker recognition (SR) methods, especially with respect to the impact of multilingual speakers and cross-age recordings. Our findings suggest that LID systems, such as Whisper, are increasingly adept at handling second-language and accented speech. However, speaker embeddings remain a fragile component of speech processing pipelines that is prone to biases related to the channel, age, and language. Issues which will need to be overcome should archives aim to employ SR methods for speaker indexing.

Topik & Kata Kunci

cs.SD cs.AI cs.CL eess.AS

Penulis (2)

Peter Sullivan

Muhammad Abdul-Mageed

Format Sitasi

APA MLA BibTeX

Sullivan, P., Abdul-Mageed, M. (2025). On Barriers to Archival Audio Processing. https://arxiv.org/abs/2507.08768

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2025
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓