This paper presents a comtmtational model of incremental utterance production in task-oriented dialogues. This model incrementally produces utterantes to propose the solution of a given problem, while simultaneously solving the problem in a stepwise manner. Even when the solution has been partially determined, this model starts utterances to satisfy time constraints where pauses in mid-utteranc...

We hypothesize that the performance of multimodal perceptive user interfaces during multi-party interaction may be improved by using facial orientation of users as a cue for identifying the addressee of a user utterance. Multi-party interactions were collected in a user test where one participant would both interact with an information kiosk and negotiate with another person about the informati...

In previous work we showed that state-of-the-art end-of-utterance detection (as used, for example, in dialog systems) can be improved significantly by making use of prosodic and/or language models that predict utterance endpoints, based on word and alignment output from a speech recognizer. However, using a recognizer in endpointing might not be practical in certain applications. In this paper ...

The present study was conducted to evaluate the accuracy affecting factors of a Mel-Frequency Cepstral Coefficients (MFCC) and Vector Quantization (VQ) based speaker recognition system. This investigation analyses the factors that affecting recognition accuracy using speech signal from day to day life in surrounding environments. It was studied the mismatch affects of text-dependency, voice sam...

To test several alternative models of verbal communication in schizophrenia, 24 schizophrenic and 24 normal speakers were shown sets of colors varying in similarity and number of colors displayed. The task was to describe a designated color in each set so that a listener could pick it out. Disturbances in schizophrenic speakers were shown to occur whenever the task demanded that they edit out n...

This letter describes a robust speech recognition system for recognizing fast speech by stretching the length of the utterance in the cepstrum domain. The degree of stretching for an utterance is determined by its rate of speech (ROS), which is based on a maximum likelihood (ML) criterion. The proposed method was evaluated on 10-digits mobile phone numbers. The results of the simulation show th...

We extracted an embedding for each word in the text sentence of the utterance using a word2vec dictionary pre-trained on a Google News corpus [3]. The text input of each utterance was formed by concatenating the word embeddings for all the words in the sentence and padding them with the appropriate zeros to have the same dimension. We set the maximum length as 60 and discard additional words (o...

This paper investigates spontaneous utterances in response to a telecom IVR prompting the caller with “Please tell me in a few words what your inquiry is about”. In responses from a typical caller base (n=29830, age-mixed) the median utterance length was 3 words. A qualitative analysis (n=74) of senior speakers (age 70+) and adult speakers (age 50 and below) revealed that seniors were significa...