A view of human-human interaction is presented and its implications for human-computer interaction discussed. Two propositions are advanced. The first is that interaction with computer systems is properly seen as mediated discourse, more akin to reading books and notices than interpersonal dialogues. The second proposition is a consequence of this, namely that unconstrained natural language is ...

Utterance rewriting aims to recover coreferences and omitted information from the latest turn of a multi-turn dialogue. Recently, methods that tag rather than linearly generate sequences have proven stronger in both in- out-of-domain settings. This is due tagger's smaller search space as it can only copy tokens dialogue context. However, these may suffer low coverage when phrases must be added ...

Hidden Markov Model is a popular statisical method that is used in continious and discrete speech recognition. The probability density function of observation vectors in each state is estimated with discrete density or continious density modeling. The performance (in correct word recognition rate) of continious density is higher than discrete density HMM, but its computation complexity is very ...

In a conversational context, user converses with system through sequence of natural-language questions, i.e., utterances. Starting from given subject, the conversation evolves sequences utterances and replies. The retrieval documents relevant to an utterance is difficult due informal use natural language in speech complexity understanding semantic context coming previous We adopt 2019 TREC Conv...

Utterance clustering is one of the actively researched topics in audio signal processing and machine learning. This study aims to improve performance utterance by multichannel (stereo) signals. Processed signals were generated combining left- right-channel a few different ways then extracting embedded features (also called d-vectors) from those processed applied Gaussian mixture model for super...