Using pronunciation-based morphological subword units to improve OOV handling in keyword search

Journal article

Out-of-vocabulary (OOV) keywords present a challenge for keyword search (KWS) systems especially in the low-resource setting. Previous research has centered around approaches that use a variety of subword units to recover OOV words. This paper systematically investigates morphology-based subword modeling approaches on seven low-resource languages. We show that using morphological subword units (morphs) in speech recognition decoding is substantially better than expanding word-decoded lattices into subword units including phones, syllables and morphs. As alternatives to grapheme-based morphs, we apply unsupervised morphology learning to sequences of phonemes, graphones, and syllables. Using one of these phone-based morphs is almost always better than using the grapheme-based morphs, but the particular choice varies with the language. By combining the different methods, a substantial gain is obtained over the best single case for all languages, especially for OOV performance.

Authors: He, Y; Baumann, P; Fang, H; Hutchinson, B; Jaech, A

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Institute of Electrical and Electronics Engineers
• Journal: IEEE/ACM Transactions on Audio, Speech and Language Processing
• Volume: 24
• Issue: 1
• Pages: 79-92
• Publication date: 2015-10-30
• DOI: 10.1109/TASLP.2015.2496222
• EISSN: 2329-9304
• ISSN: 2329-9290
• Keywords: out-of-vocabulary (OOV) words; SBTMR; morphological analysis; keyword search; speech recognition; subword units; graphones