Topic identification of spoken documents using unsupervised acoustic unit discovery

Santosh Kesiraju; Raghavendra Pappagari; Lucas Ondel; Lukás Burget; Najim Dehak; Sanjeev Khudanpur; Jan Cernocký; Suryakanth V. Gangashetty

ICASSP 2017accepted0 citations

Topic identification of spoken documents using unsupervised acoustic unit discovery

Santosh Kesiraju, Raghavendra Pappagari, Lucas Ondel, Lukás Burget, Najim Dehak, Sanjeev Khudanpur, Jan Cernocký, Suryakanth V. Gangashetty

Source ↗

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.

BibTeX

@inproceedings{icassp2017_topicidentificat,
  title = {Topic identification of spoken documents using unsupervised acoustic unit discovery},
  author = {Santosh Kesiraju and Raghavendra Pappagari and Lucas Ondel and Lukás Burget and Najim Dehak and Sanjeev Khudanpur and Jan Cernocký and Suryakanth V. Gangashetty},
  booktitle = {ICASSP 2017},
  year = {2017}
}