Efficient subword lattice retrieval for German spoken term detection

We present a lattice-based STD method for German broadcast news data and compare it to a previously proposed fuzzy search. Due to the important out-of-vocabulary (OOV) problem in German, we evaluate suitable subword indexing units for lattice retrieval. Hybrid lattice retrieval of words and subwords is investigated because of the robust nature of words as an indexing unit. We show that by using efficient lattice graph and score pruning techniques, precision of subword retrieval is increased by 8% absolute with only a small loss in recall. Additionally, a speed-up of up to 6 times can be observed.