JUPlTER: a telephone-based conversational interface for weather information

By Victor W. Zue, S. Seneff, James R. Glass, J. Polifroni, Christine Pao, Timothy J. Hazen, I. L. Hetherington. IEEE Transactions on Speech and Audio Processing, 2000

558 citations recorded by the source corpus.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/e22ffd1dbbf9dca915ee167c502788029ef19bba

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Out-of-Domain Utterance Detection Using Classification Confidences of Multiple Topics (2007, methodology): “Next, a set of SVM (support vector machine) classification models (one for each topic class t1 ,...,t M ) are applied to W and confidence scores C(tj|W ) in the range [0, 1 ] are calculated.”
Modeling out-of-vocabulary words for robust speech recognition (2000, methodology): “For example, in our JUPITER weather information domain the OOV rate is approximately 2%, and over 13% of the utterances contain OOV words [12].”
Automatic Speech Recognition - A Brief History of the Technology Development (2004, background): “Among these systems, Pegasus and Jupiter developed at the Massachusetts Institute of Technology under Victor Zue were particularly noteworthy demos [52,53], and the How May I Help You (HMIHY) system at AT&T developed by Al Gorin was an equally noteworthy service that was introduced as part of AT&T C”
The Technology Behind Personal Digital Assistants: An overview of the system architecture and key components (2017, background): “It can also be used for addressing the errors and disfluencies introduced by a speech recognizer [28], [49].”
Discriminative Training for Large-Vocabulary Speech Recognition Using Minimum Classification Error (2007, background): “JUPITER is a telephone-based conversational system that can understand and respond to queries related to weather forecasts for roughly 500 cities around the world [67].”
A probabilistic framework for segment-based speech recognition (2003, methodology): “Although one could explore an exhaustive segmentation method (i.e., one that could consider all possible segmentations), we have typically used explicit segmentation algorithms in our research, mainly because of our interest in real-time ASR for conversational interfaces ( Zue et al., 2000 ).”
The Dialog State Tracking Challenge Series: A Review (2016, methodology): “For example, the MIT JUPITER weather information system maintained a set of state variables which were updated using hand-written rules in a dialog control table (Zue et al., 2000).”
End-to-End Task-Completion Neural Dialogue Systems (2017, background): “Traditional systems have a rather complex and modularized pipeline, consisting of a language understanding (LU) module, a dialogue manager (DM), and a natural language generation (NLG) component (Rudnicky et al., 1999; Zue et al., 2000; Zue and Glass, 2000).”
Learning Lexicons From Speech Using a Pronunciation Mixture Model (2013, methodology): “For this reason, the experiments in this work will expand upon those performed in [2] on the weather query corpus [30].”
Machine Learning for Dialog State Tracking: A Review (2015, methodology): “Early spoken dialog systems used hand-crafted rules for DST, keeping a single top hypothesis for each component of the dialog state, often with corresponding confidence scores [6, 7].”
Discovering linguistic structures in speech: models and applications (2014, methodology): “All the speech recognition experiments reported in this paper are performed on a weather query dataset, which consists of narrow-band, conversational telephone speech [195].”
Dialog State Tracking with Reinforced Data Augmentation (2019, methodology): “methods can be classified into three categories: rule-based (Zue et al., 2000), generative (DeVault and Stone, 2007; Williams, 2008), and discriminative (Metallinou et al.”
Effective Data Augmentation Approaches to End-to-End Task-Oriented Dialogue (2019, background): “Task-oriented dialogue systems have evolved from traditional modularized pipeline architectures [1], [2], [3] to recent end-to-end trainable frameworks [4], [5], [6].”
End-to-end Audio Visual Scene-aware Dialog Using Multimodal Attention-based Video Features (2018, background): “ dialog technologies have been applied in real-world human-machine interfaces including smart phone digital assistants, car navigation systems, voice-controlled smart speakers, and humanfacing robots [1, 2, 3]. Generally, a dialog system consists of a pipeline of data processing modules, including a”
Statistical language model adaptation: review and perspectives (2004, background): “Many systems in use today, especially for complex dialog applications, are based on the former (cf., for example, Riccardi and Gorin, 2000; Zue et al., 2000), while the latter is more prevalent amongst transcription systems (see e.”
Natural language question answering: the view from here (2001, methodology): “For example, MIT’s Jupiter system provides a telephone-based conversational interface for international weather information (Zue et al. , 2000) 5 .”