The challenge of non-lexical speech sounds

Non-lexical speech sounds (conversational grunts), such as uh-huh, un-hn, mm, and oh, are common in English. In human dialogs these sounds are important in conversation control and for conveying attitudes. Spoken dialog systems may make use of these sounds to achieve concise, smooth, relaxed interactions. Doing so is, however, a challenge, because most algorithms used in spoken language processing were devised for words, but grunts are di erent from words both phonetically and semantically. For example, the phonetic inventory is di erent, superimposition of phonemes occurs, the set of conversational grunts is productive rather than nite, and the meanings are compositional and involve sound-symbolism.