Object Recognition Using Environmental Cues Mentioned Explicitly or Implicitly in Speech
نویسندگان
چکیده
The service robot that carries out tasks ordered by the users through speech needs a vision system to recognize the objects appearing in the orders and a speech interface for natural communication with the user. The user’s order may be explicit or implicit. The speech interfaces should have a capability of dealing with explicit as well as implicit utterances. In this paper, we present ‘how environmental cues help in understanding user’s orders.’ We assume that humans usually put a particular object on a small number of places in the environment. Using the environmental knowledge, the robot can efficiently understand and accomplish the user’s demand with less vision task and user burden.
منابع مشابه
خاک و خِرَد، تأملی در شأن معماری در مثنوی معنوی
Rumi was not an architect or architectural theorician. However in his Mathnawi, he dealt in architecture, explicitly or implicitly, intentionally or unintentionally. It can be seen in Mathnawi in diferrent levels: when he talks about the built environment in which he used to live when he uses architecture elements and spaces as figure of speech when he borrows an architectural metaphor in talki...
متن کاملSpeaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کاملSpeaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کاملPronunciation Modeling for Large Vocabulary Speech Recognition by Arthur
The large pronunciation variability of words in conversational speech is one of the major causes of low accuracy for automatic speech recognition (ASR). Many pronunciation modeling approaches have been developed to address this problem. Some explicitly manipulate the pronunciation dictionary as well as the set of the units used to define the pronunciations of words. Others model the pronunciati...
متن کاملThe Effects of Culture and Gender on the Recognition of Emotional Speech: Evidence from Persian Speakers Living in a Collectivist Society
This paper reports on a behavioral study that explores the role of culture and gender in the recognition of emotional speech in an under investigated cultural context (a collectivist society: i.e., Iran). Participants were asked to recognize the emotional prosody of a set of validated emotional vocal portrayals (including the five basic emotions). Findings of the experiment were then comp...
متن کامل