14th International Congress of Phonetic Sciences (ICPhS-14) San Francisco, CA, USA August 1-7, 1999

Investigation of Language Structure by means of Language Models Incorporating Breathing and Articulatory Noise

Karl Weilhammer (1), Florian Schiel (1,2)

(1) Department of Phonetics and Speech Communication, University of Munich, Germany
(2) Bavarian Archive for Speech Signals, University of Munich, Germany

In our experiment we used a bigram language model and a standard speech recogniser to test if linguistic information is related to the position of silence, articulatory noise, background noise, laughing and breathing in spontaneous speech.
   We observed that for silence and articulatory noise the acoustic modelling is more important than linguistic information represented in the bigrams of a language model. Breathing carries useful information that can be described in a language model, because including it into the language model improves test set perplexity and recognition accuracy.
   This means that precisely defined noise items add some linguistic knowledge to the language model and contribute to a better performance of an automatic speech recogniser.

Full Paper

Bibliographic reference.  Weilhammer, Karl / Schiel, Florian (1999): "Investigation of language structure by means of language models incorporating breathing and articulatory noise", In ICPhS-14, 1649-1652.