Spoken term detection using the segment quantization of acoustic features of spoken documents
- T. Matsunaga, K. Cho, Y. Yamashita
- In Proceedings of the 6th Spoken Document…
This paper describes improvement of the STD method which is based on the vector quantization (VQ). Spoken documents are represented as sequences of VQ codes, and they are matched with a text query to be detected based on the V-P score which measures the relationship between a VQ code and a phoneme. The matching score between VQ codes and phonemes is calculated after normalization for each phoneme in a query term to avoid biased scoring particular phonemes. 1. Objectives -To improve the detection performance of unknown words for the spoken term detection (STD). 2. STD Method Based on Vector Quantization To represent spoken documents as sequences of VQ codes . > Conventional methods represent spoken documents as sequences of sub-words, such as phonemes, to detect unknown words.