Ninth International Conference on Spoken Language Processing

Pittsburgh, PA, USA
September 17-21, 2006

Discriminative Named Entity Recognition of Speech Data Using Speech Recognition Confidence

Katsuhito Sudoh, Hajime Tsukada, Hideki Isozaki

NTT Corporation, Japan

This paper presents a method for the named entity recognition (NER) of speech data that uses automatic speech recognition (ASR) confidence as a feature that indicates whether each word is correctly recognized. An NER model is trained using ASR results with named entity (NE) labels to include an ASR confidence feature as well as corresponding transcriptions with NE labels. Experiments using support vector machines (SVMs) and speech data from Japanese newspaper articles show that the proposed method achieves higher F-measure in NER than a simple application of text-based NER to ASR results.

Full Paper

Bibliographic reference.  Sudoh, Katsuhito / Tsukada, Hajime / Isozaki, Hideki (2006): "Discriminative named entity recognition of speech data using speech recognition confidence", In INTERSPEECH-2006, paper 1153-Mon2WeO.5.