Bell Labs Approach to Aurora Evalua Recognition
نویسندگان
چکیده
In this paper we study various front-end features, modeling and adaptation algorithms on the Aurora 3 databases, including auditory, moment, and AM-FM modulation features, context-dependent digit models, segmental K-means training, discriminative training, and model adaptations. The evaluation results on Aurora 3 are presented with a brief summary of our Aurora 2 results.
منابع مشابه
Evaluating the Aurora connected digit recognition task - a bell labs approach
Connected digit recognition has always been an ideal task for fundamental research in speech recognition due to its relatively low complexity and potential applications. In Bell Labs we have developed a number of techniques targeting directly or indirectly at connected digit recognition. For the Aurora task, we study a few such algorithms for the entire spectrum of the issues, including feature...
متن کاملA Utility-Based Approach to Intention Recognition
Based on the assumption that a rational agent will adopt a plan that maximizes the expected utility, we present a utility-based approach to plan recognition problem in this paper. The approach explicitly takes the observed agent’s preferences into consideration, and computes the estimated expected utilities of plans to disambiguate competing hypotheses. Online plan recognition is realized by in...
متن کاملDescription of the Bell Labs Intonation System
This paper describes the approach to intonation modeling currently used in the Bell Labs Multi-lingual Text-to-Speech System for English, French, German, Italian, Spanish, Russian, Romanian, and Japanese.
متن کاملDiscriminatively Reranking Abductive Proofs for Plan Recognition
We investigate the use of a simple, discriminative reranking approach to plan recognition in an abductive setting. In contrast to recent work, which attempts to model abductive plan recognition using various formalisms that integrate logic and graphical models (such as Markov Logic Networks or Bayesian Logic Programs), we instead advocate a simpler, more flexible approach in which plans found t...
متن کاملAppears at the AAMAS 2004 Workshop on Agent Tracking: Modeling Other Agents from Observations A Utility-Based Approach to Intention Recognition
Based on the assumption that a rational agent will adopt a plan that maximizes the expected utility, we present a utility-based approach to plan recognition problem in this paper. The approach explicitly takes the observed agent’s preferences into consideration, and computes the estimated expected utilities of plans to disambiguate competing hypotheses. Online plan recognition is realized by in...
متن کامل