Optimization of Neural Network Language Models for keyword search

• Published in: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 4888 - 4892
• Main Authors: Gandhe, Ankur, Metze, Florian, Waibel, Alex, Lane, Ian
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-05-2014
• Subjects: Artificial neural networks; Computational modeling; History; Keyword search; language modeling; neural networks; Speech recognition; Training
• ISSN: 1520-6149; 2379-190X
• DOI: 10.1109/ICASSP.2014.6854531

Recent works have shown Neural Network based Language Models (NNLMs) to be an effective modeling technique for Automatic Speech Recognition. Prior works have shown that these models obtain lower perplexity and word error rate (WER) compared to both standard n-gram language models (LMs) and more advanced language models including maximum entropy and random forest LMs. While these results are compelling, prior works were limited to evaluating NNLMs on perplexity and word error rate. Our initial results showed that while NNLMs improved speech recognition accuracy, the improvement in keyword search was negligible. In this paper we propose alternate optimizations of NNLMs for the task of keyword search. We evaluate the performance of the proposed methods for keyword search on the Vietnamese dataset provided in phase one of the BABEL 1 project and demonstrate that by penalizing low frequency words during NNLM training, keyword search metrics such as actual term weighted value (ATWV) can be improved by up to 9.3% compared to the standard training methods.