On Barriers to Archival Audio Processing
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Language IdentificationSpeaker RecognitionSimilar Papers 제목 키워드 기반
Keyword spotting for audiovisual archival search in Uralic languages
Automated speech tools for helping communities process restricted-access corpora for language revival efforts
Many archival recordings of speech from endangered languages remain unannotated and inaccessible to community members and language learning programs. One bottleneck is the time-intensive nature of annotation. An even nar…
Action DetectionActivity DetectionAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)+5AI Blob! LLM-Driven Recontextualization of Italian Television Archives
This paper introduces AI Blob!, an experimental system designed to explore the potential of semantic cataloging and Large Language Models (LLMs) for the retrieval and recontextualization of archival television footage. D…
Speech RecognitionPOST: Email Archival, Processing and Flagging Stack for Incident Responders
Phishing is one of the main points of compromise, with email security and awareness being estimated at \$50-100B in 2022. There is great need for email forensics capability to quickly search for malicious content. A nove…
Multimodal LLMs for Historical Dataset Construction from Archival Image Scans: German Patents (1877-1918)
We leverage multimodal large language models (LLMs) to construct a dataset of 306,070 German patents (1877-1918) from 9,562 archival image scans using our LLM-based pipeline powered by Gemini-2.5-Pro and Gemini-2.5-Flash…