13th Annual Conference of the International Speech Communication Association

Portland, OR, USA
September 9-13, 2012

Subword Speech Recognition for Detection of Unseen Words

Ivan Bulyko, José Herrero, Chris Mihelich, Owen Kimball

Raytheon BBN Technologies, Cambridge, MA, USA

We present a novel approach to building a subword speech recognizer for the task of phonetic keyword search. The recognizer, which uses short fixed-length phonetic units, is trained with phonetic transcripts that are segmented into all possible substrings of 1, 2 and 3 phones, using a lattice representation to accommodate the overlapping units. We compare the keyword search accuracy of the proposed system with systems that use words, graphones, variable-length phonetic units and context-dependent phones. Experiments with Spanish CTS data show that the proposed subword recognizer outperforms other subword systems in terms of phonetic keyword search accuracy measured on queries that consist of words not present in the training data.

Index Terms: speech recognition, keyword search, OOV

Full Paper

Bibliographic reference.  Bulyko, Ivan / Herrero, José / Mihelich, Chris / Kimball, Owen (2012): "Subword speech recognition for detection of unseen words", In INTERSPEECH-2012, 2446-2449.