{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/open-source-german-distant-speech-recognition","title":"Open Source German Distant Speech Recognition: Corpus and Acoustic Model","arxiv_id":null,"date":"2015-12-11","proceeding":"International Conference on Text, Speech, and Dialogue 2015 12","authors":["Stephan Radeck-Arneth","Benjamin Milde","Arvid Lange","Evandro Gouvea","Stefan Radomski","Max Mühlhäuser","and Chris Biemann"],"abstract":"We present a new freely available corpus for German distant speech recognition and report speaker-independent word error rate (WER) results for two open source speech recognizers trained on this corpus. The corpus has been recorded in a controlled environment with three different microphones at a distance of one meter. It comprises 180 different speakers with a total of 36 hours of audio recordings. We show recognition results with the open source toolkit Kaldi (20.5% WER) and PocketSphinx (39.6% WER) and make a complete open source solution for German distant speech recognition possible.","url_abs":"https://link.springer.com/chapter/10.1007/978-3-319-24033-6_54","url_pdf":"https://download.hrz.tu-darmstadt.de/pub/FB20/Dekanat/Publikationen/LangTech/Radeck-ArnethEtAl_TSD2015_SpeechCorpus.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"open-source-german-distant-speech-recognition","repo_url":"https://github.com/tudarmstadt-lt/kaldi-tuda-de","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"distant-speech-recognition","task_name":"Distant Speech Recognition"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[{"slug":"tuda","name":"TUDA","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-recognition-on-tuda","task":"Speech Recognition","dataset":"TUDA","model":"Kaldi","rank_in_archive_order":8,"of":9,"metrics":{"Test WER":"20.5%"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-tuda","task":"Speech Recognition","dataset":"TUDA","model":"PocketSphinx","rank_in_archive_order":9,"of":9,"metrics":{"Test WER":"39.6%"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}