Topic identification of spoken documents using unsupervised acoustic unit discovery

Santosh Kesiraju, Raghavendra Pappagari, Lucas Ondel, Lukáš Burget, Najim Dehak, Sanjeev Khudanpur, Jaň Černocký, Suryakanth Gansgashetty

2017 · 14 citations · 19 references

Concepts

Abstract

This paper investigates the application of unsupervised acoustic unit discovery for topic identification (topic ID) of spoken audio documents. The acoustic unit discovery method is based on a non-parametric Bayesian phone-loop model that segments a speech utterance into phone-like categories. The discovered phone-like (acoustic) units are further fed into the conventional topic ID framework. Using multilingual bottleneck features for the acoustic unit discovery, we show that the proposed method outperforms other systems that are based on cross-lingual phoneme recognizer.

References

19