7th International Conference on Spoken Language Processing

September 16-20, 2002
Denver, Colorado, USA

Building an ASR System for Noisy Environments: SRI’s 2001 SPINE Evaluation System

Venkata Ramana Rao Gadde, Andreas Stolcke, Dimitra Vergyri, Jing Zheng, Kemal Sönmez, Anand Venkataraman

SRI International, USA

We describe SRI’s recognition system as used in the 2001 DARPA Speech in Noisy Environments (SPINE) evaluation. The SPINE task involves recognition of speech in simulated military environments. The task had some unique challenges, including segmentation of foreground speech from noisy background, the need for robust acoustic models to handle noisy speech, and development of language models from limited training data. In developing the SRI evaluation system for this task, we addressed each of these challenges using a combination of state-of-the-art techniques, including several types of feature normalization, model adaptation, class-based language modeling, multi-pass segmentation and recognition, and word posterior-based decoding and system combination.


Full Paper

Bibliographic reference.  Gadde, Venkata Ramana Rao / Stolcke, Andreas / Vergyri, Dimitra / Zheng, Jing / Sönmez, Kemal / Venkataraman, Anand (2002): "Building an ASR system for noisy environments: SRI’s 2001 SPINE evaluation system", In ICSLP-2002, 1577-1580.