This paper presents an approach for automatically learning reference resolution, which involves using natural language expressions, including spatial language descriptions, to refer to an object in a context. This is useful in conversational systems that need to understand the context of an utterance, like multi-modal or embodied dialogue systems. Markov Logic Networks are explored as a way of ...

We propose a context-sensitive method to predict noun-phrases ill the next utterance of a telephone inquiry dialogue. First, information about tile utterance type and the discourse entities of the next utterance is graspcd using a dialogue interpretation model. Second, a domain-dependent knowledge base for noun-phrase usage is developed , focusing on the dialogue situations in context. Finally,...

Previous ERP studies have often reported two ERP components-LAN and P600-in response to subject-verb (S-V) agreement violations (e.g., the boys (*) runs). However, the latency, amplitude and scalp distribution of these components have been shown to vary depending on various experiment-related factors. One factor that has not received attention is the extent to which the relative perceptual sali...

This paper proposes a method for topic detection of an utterance for speech dialogue processing including speech translation. There are three important points to consider in realizing topic detection of an utterance. The first is to obtain information from a short utterance. The second is to deal with a broad topic. The third is to have robustness against speech recognition errors. Our topic de...

Speaker Verification and Utterance Verification are examples of techniques that can be used for Speaker Authentication purposes. Speaker Verification consists of accepting or rejecting the claimed identity of a speaker by processing samples of his/her voice. Usually, these systems are based on HMM models that try to represent the characteristics of the speakers’ vocal tracts. Utterance Verifica...

Recently, attention mechanism based deep learning has gained much popularity in speech recognition and natural language processing due to its flexibility at the decoding phase. Through the attention mechanism, the relevant encoding context vectors contribute a majority portion to the construction of the decoding context, while the effect of the irrelevant ones is minimized. Inspired by this ide...

A digital pursuit rotor was used to monitor speech planning and production costs by time-locking tracking performance to the auditory wave form produced as young and older adults were describing someone they admire. The speech sample and time-locked tracking record were segmented at utterance boundaries and multilevel modeling was used to determine how utterance-level predictors such as utteran...

This paper describes a computationally simple method to perform text independent speaker verification using second order statistics. The suggested method, called utterance level scoring (ULS), allows obtaining a normalized score using a single pass through the frames of the tested utterance. The utterance sample covariance is first calculated and then compared to the speaker covariance using a ...