Investigating cross-language speech retrieval for a spontaneous conversational speech collection

Abstract

Cross-language retrieval of spontaneous speech combines the challenges of working with noisy automated transcription and language translation. The CLEF 2005 Cross-Language Speech Retrieval (CL-SR) task provides a standard test collection to investigate these challenges. We show that we can improve retrieval performance: by careful selection of the term weighting scheme; by decomposing automated transcripts into phonetic substrings to help ameliorate transcription errors; and by combining automatic transcriptions with manually-assigned metadata. We further show that topic translation with online machine translation resources yields effective CL-SR.