Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

Detecting Acoustic Morphemes in Lattices for Spoken Language Understanding

Dijana Petrovska-Delacrétaz, Allen L. Gorin, Jerry H. Wright, Giuseppe Riccardi

AT&T Labs, Speech Research, Florham Park, NJ, USA

Current methods for training statistical language models for recognition and understanding require large annotated corpora. The collection, transcription and labeling of such corpora is a major bottleneck for creating new applications and for refinements of existing ones. Thus, it is of great interest to develop methods for automatically learning vocabulary, grammar and semantics from a speech corpus without transcriptions. In this paper we report on an experiment where acoustic morphemes are automatically acquired from the output of a task-independent phone recognizer. The utility of these units is experimentally evaluated for call-type classification in the ’How may I help you?’ task. Detected occurrences of the acoustic morphemes in the lattice output provide the basis for the classification of the test sentences. Using lattices, we achieve a reduction of 59% from the false rejection rate using best paths, albeit with a 5% reduction in the correct classification performance from that baseline.

Keywords: Spoken language understanding, Salient phrase acquisition, Acoustic morphemes, Phone lattices.


Full Paper

Bibliographic reference.  Petrovska-Delacrétaz, Dijana / Gorin, Allen L. / Wright, Jerry H. / Riccardi, Giuseppe (2000): "Detecting acoustic morphemes in lattices for spoken language understanding", In ICSLP-2000, vol.4, 53-56.