• Publications
  • Influence
Expanding the Scope of the ATIS Task: The ATIS-3 Corpus
TLDR
The migration of the ATIS task to a richer relational database and development corpus (ATIS-3) and the ATis-3 corpus is described, including breakdowns of data by type (e.g. context-independent, context-dependent, and unevaluable) and variations in the data collected at different sites. Expand
Pocketsphinx: A Free, Real-Time Continuous Speech Recognition System for Hand-Held Devices
TLDR
This paper presents a preliminary case study on the porting and optimization of CMU Sphinx-11, a popular open source large vocabulary continuous speech recognition (LVCSR) system, to hand-held devices, and is believed to be the firsthand-held LVCSR system available under an open-source license. Expand
The RavenClaw dialog management framework: Architecture and systems
TLDR
RavenClaw isolates the domain-specific aspects of the dialog control logic from domain-independent conversational skills, and in the process facilitates rapid development of mixed-initiative systems operating in complex, task-oriented domains. Expand
The Second Conversational Intelligence Challenge (ConvAI2)
TLDR
To improve performance on multi-turn conversations with humans, future systems must go beyond single word metrics like perplexity to measure the performance across sequences of utterances (conversations)—in terms of repetition, consistency and balance of dialogue acts. Expand
Ravenclaw: dialog management using hierarchical task decomposition and an expectation agenda
TLDR
RavenClaw is described, a new dialog management framework developed as a successor to the Agenda architecture used in the CMU Communicator, and allows rapid development of dialog management components for spoken dialog systems operating in complex, goal-oriented domains. Expand
Olympus: an open-source framework for conversational spoken language interface research
TLDR
Olympus, a freely available framework for research in conversational interfaces, is introduced, describing the overall architecture, several systems spanning different domains, and a number of current research efforts supported by Olympus. Expand
Word level confidence annotation using combinations of features
TLDR
In comparing different classification techniques, it is found that Support Vector Machines (SVMs) appear to provide the best accuracy, and two parse-level features, Parsing-Mode and SlotBackoff-Mode, provide annotation accuracy comparable to that observed for decoder- level features. Expand
Auditory segregation: stream or streams?
TLDR
An affirmative answer is suggested by the observation that the organizational structure of the unattended material interacts with the structure of material to which the subject is trying to attend. Expand
Stochastic Language Generation for Spoken Dialogue Systems
TLDR
This paper proposes a new corpus-based approach to natural language generation, specifically designed for spoken dialogue systems, that is based on template-based and rule-based NLG approaches. Expand
Sorry and I Didn’t Catch That! - An Investigation of Non-understanding Errors and Recovery Strategies
TLDR
An extensive empirical analysis of non-understanding errors and ten non-Understanding recovery strategies, based on a corpus of dialogs collected with a spoken dialog system that handles conference room reservations, finds that dialog performance can be improved by using a smarter policy for engaging the non- Understood recovery strategies. Expand
...
1
2
3
4
5
...