We compare and contrast two different models for detecting sentence-like units in continuous speech. The first approach uses hidden Markov sequence models based on N-grams and max...
Yang Liu, Andreas Stolcke, Elizabeth Shriberg, Mar...
This paper describes a new approach to modeling duration for LVCSR using SCARF, a toolkit for speech recognition with segmental conditional random fields. We utilize SCARF’s abi...
Abstract-- Identification of output error models from frequency domain data generally results in a non-convex optimization problem. A well-known method to approach the output error...
Advanced applications in fields like electronic publishing and telecooperation face the problem of handling multimedia information. Conventional database systems do not offer adeq...
Abstract. A communication system evolves dynamically with the addition and deletion of services. In our previous work [12], a graph transformation system (GTS) was used to model th...