Query word retrieval from continuous speech using GMM posteriorgrams

Reddy, P R and Rout, K and Kodukula, Sri Rama Murty (2014) Query word retrieval from continuous speech using GMM posteriorgrams. In: 2014 International Conference on Signal Processing and Communications (SPCOM), 22-25 July 2014, Benguluru, India.

[img] PDF
1274_query_Rout_2014_IEEE.pdf - Published Version
Restricted to Registered users only

Download (185kB) | Request a copy


The objective of this work is to study the issues involved in building an automatic query word retrieval system for broadcast news in an unsupervised framework, i.e., without using any labelled speech data. In the absence of labelled data, sequence of feature-vectors extracted from the query word have to be matched with those extracted from the test utterance. This is a non-trivial task, as typical feature-vectors like Mel-frequency cepstral coefficients (MFCC) carry both speech-specific and speaker-specific information. In this work, we have employed Gaussian mixture models (GMM) to extract speaker-independent features from the speech signal. Gaussian mixture model, trained on a large amount of speech data, is used to derive posterior features for each frame of speech signal. The sequence of posterior features are matched using dynamic time-warping algorithm to detect the presence of query word in the test utterance. The performance of the proposed method is evaluated on Telugu broadcast news database. It is observed that the posterior features extracted from GMM are better suited for query word retrieval compared to the MFCC features.

[error in script]
IITH Creators:
IITH CreatorsORCiD
Kodukula, Sri Rama Murtyhttps://orcid.org/0000-0002-6355-5287
Item Type: Conference or Workshop Item (Paper)
Subjects: Physics > Electricity and electronics
Divisions: Department of Electrical Engineering
Depositing User: Team Library
Date Deposited: 30 Dec 2014 05:49
Last Modified: 05 Dec 2017 04:06
URI: http://raiith.iith.ac.in/id/eprint/1274
Publisher URL: https://doi.org/10.1109/SPCOM.2014.6984011
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 1274 Statistics for this ePrint Item