Boulder Language Technologies

Spoken Dialogs for Enabling Spoken Dialogs with Virtual Humans

CSLR is developing a free toolkit to support research and development of programs that incorporate spoken dialog interaction with lifelike computer characters.

SONIC: Large Vocabulary Speech Recognition System

SONIC is a large vocabulary speech recognition system used in a number of research projects at CSLR. The software is being made available for non-commercial use. Executables are provided for Linux (kernel 2.2/2.4), MS Windows, Sun Solaris, and Mac OS X. For more information about speech recognition research at CSLR and the SONIC LVCSR system (click here )

AQUAINT

This project is funded by ARDA and is a collaboration between CSLR and Columbia University. We are developing an integrated system for answering complex questions; these are questions that require interacting with the user to refine and clarify the context of the question, whose answer may be located in non­homogenous databases of speech and text, and for which presenting the answer requires combining and summarizing information from multiple sources and over time. We are developing an integrated statistical and semantic approach by integrating multiple models of the information in the text at the word, clause, event, and document level. We will automatically derive links between related events and descriptions and associate questions with multiple answers even when the answer uses very different terms than those in the question. Generating a satisfactory answer to complex questions requires the ability to collect all relevant answers from multiple documents in different media, intelligently weigh their relative importance, and generate a coherent summary of the multiple facts and opinions reported. We are investigating new paradigms for the organization and presentation of information, including a detailed, yet efficiently computable semantic model, and an event­based model for organizing and linking parts of documents. This will be coupled with innovations in the processing of spoken material, modeling of the context for handling connected questions and answers (such as follow­ups and clarifications) within a session, and summarization technology for combining hundreds or thousands of potentially related text pieces while eliminating redundancies and identifying conflicts and contradictions.

CU Communicator Project

CU Communicator is a conversational dialogue system that interacts with users over the telephone to provide information on air travel, hotel and rental car reservations. This system serves as a test bed for our research to improve the state of the art in spoken dialogue systems. This project is funded by the Defense Advanced Research Projects Agency (DARPA). For more information on the CU Communicator Project, click here .

CU Move: DARPA In-Vehicle Automatic Speech Recognition & Navigation System

The goal of the CU-Move project is to develop algorithms and technology for robust access to information via spoken dialog systems in mobile, hands free environments. The novel aspects include the formulation of a new microphone array and multi-channel noise suppression front-end, corpus development for speech and acoustic vehicle conditions, environmental classification for changing in-vehicle noise conditions, and a back-end dialog navigation information retrieval sub-system connected to the WWW. While previous attempts at in-vehicle speech systems have generally focused on isolated command words to set radio frequencies, temperature control, etc., the CU-Move system is focused on natural conversational interaction between the user and in-vehicle system. System advances include intelligent microphone arrays, auditory and speaker based constrained speech enhancement methods, environmental noise characterization, and speech recognizer model adaptation methods for changing acoustic conditions in the car. Our initial prototype system allows users to get driving directions for the Boulder area via a hands free cell phone, while driving in a car. For more information on the CU Move Project, click here .