Learning lexicons from spoken utterances based on statistical model selection

Learning Place-Names from Spoken Utterances and Localization Results by Mobile Robot

This paper proposes a method for the unsupervised learning of place-names from pairs of a spoken utterance and a localization result, which represents a current location of a mobile robot, without any priori linguistic knowledge other than a phoneme acoustic model. In previous work, we have proposed a lexical learning method based on statistical model selection. This method can learn the words ...

Learning Physically Grounded Lexicons from Spoken Utterances

Classification-based spoken text selection for LVCSR language modeling

Large vocabulary continuous speech recognition (LVCSR) has naturally been demanded for transcribing daily conversations, while developing spoken text data to train LVCSR is costly and time-consuming. In this paper, we propose a classification-based method to automatically select social media data for constructing a spoken-style language model in LVCSR. Three classification techniques, SVM, CRF,...

Learning to personalize spoken generation for dialogue systems

One of the most robust findings of studies of human-human dialogue is that people adapt their utterances to their conversational partners. However, spoken language generators are limited in their ability to adapt to individual users. While statistical models of language generation have the potential for individual adaptation, we know of no experiments showing this. In this paper, we utilize one...

Neural Belief Tracker: Data-Driven Dialogue State Tracking

One of the core components of modern spoken dialogue systems is the belief tracker, which estimates the user’s goal at every step of the dialogue. However, most current approaches have difficulty scaling to larger, more complex dialogue domains. This is due to their dependency on either: a) Spoken Language Understanding models that require large amounts of annotated training data; or b) hand-cr...