15th Annual Conference of the International Speech Communication Association

September 14-18, 2014

Improving Named Entity Recognition with Prosodic Features

Denys Katerenchuk, Andrew Rosenberg

CUNY Graduate Center, USA

In natural language processing (NLP) the problem of named entity (NE) recognition in speech is well known, yet remains a challenge where performance is dependent on automatic speech recognition (ASR) system error rates. NEs are often foreign or out-of-vocabulary (OOV) words, leaving conventional ASR systems unable to recognize them. In our research, we improve a CRF-based NE recognition system by incorporating two styles of prosodic features, hypothesized ToBI labels and unsupervised clusters of acoustic features. ToBI-based features improve NE recognition by 6% absolute (F1:0.39 v.s. F1: 0.45) on automatically recognized spontaneous speech from ACE'05.

Full Paper

Bibliographic reference.  Katerenchuk, Denys / Rosenberg, Andrew (2014): "Improving named entity recognition with prosodic features", In INTERSPEECH-2014, 293-297.