Invariant-integration method for robust feature extraction in speaker-independent speech recognition

Florian Müller, Alfred Mertins


The vocal tract length (VTL) is one of the variabilities that speaker-independent automatic speech recognition (ASR) systems encounter. Standard methods to compensate for the effects of different VTLs within the processing stages of the ASR systems often have a high computational effort. By using an appropriate warping scheme for the frequency centers of the time-frequency analysis, a change in VTL can be approximately described by a translation in the subband-index space. We present a new type of features that is based on the principle of invariant integration, and an according feature selection method is described. ASR experiments show the increased robustness of the proposed features in comparison to standard MFCCs.
Original languageEnglish
Title of host publicationProc. Interspeech 2009
Number of pages4
Publisher International Speech Communication Association (ISCA)
Publication date01.09.2009
Publication statusPublished - 01.09.2009
Event10th Annual Conference of the International Speech Communication Association - Brighton, United Kingdom
Duration: 06.09.200910.09.2009
Conference number: 78744


Dive into the research topics of 'Invariant-integration method for robust feature extraction in speaker-independent speech recognition'. Together they form a unique fingerprint.

Cite this