@InProceedings{Mengistu2007_475,
<br/>   author = {Kinfe Tadesse Mengistu and Martin Schafföner and Andreas Wendemuth},
<br/>   booktitle = {Studientexte zur Sprachkommunikation: Elektronische Sprachsignalverarbeitung 2007},
<br/>   title = {Gender Recognition and Gender-based Acoustic Model Adaptation for Telephone-based Spoken Dialog System},
<br/>   year = {2007},
<br/>   editor = {Klaus Fellbaum},
<br/>   month = mar,
<br/>   pages = {68--75},
<br/>   publisher = {TUDpress, Dresden},
<br/>   abstract  = {In this paper we describe the speech recognition component of a telephonebased
spoken dialog system that uses HTK-based speech recognizer integrated in a
VoiceXML framework and an ISDN telephone interface. As the speech recognizer
component is one of the most decisive components that determine the usefulness and
user acceptance of a dialog system, we present here strategies on how to build and
improve the performance of a speech recognition component within such a system. The
baseline speaker-independent system gives a word error rate (WER) of 13.66% for
female speakers and 21.55% for male speakers using a 22-hour telephone speech from
the Communicator 2001 Evaluation corpus. As can be observed, the system appears
biased towards female speakers. This is attributed to the fact that the number of female speakers used in training the models is significantly higher than male speakers (72 vs. 28). To combat this problem and to improve the performance of the system for male speakers, we use two approaches. First, taking the presence of within-gender acoustic similarity due to similar vocal mechanism of speakers into consideration, we adapt the speaker independent HMMs using adaptation data from each gender. As an alternative, separate gender-dependent models are built. We also built a Gaussian Mixture Model (GMM) gender classifier that can determine the gender of the speaker given a very short utterance (typically a “yes” or a “no”) with 96.62% accuracy.},
<br/>   isbn = {978-3-940046-40-6},
<br/>   issn = {0940-6832},
<br/>   keywords = {Spracherkennung},
<br/>   url = {https://www.essv.de/pdf/2007_68_75.pdf},
<br/>}