Practical implementations of computational theories of speech and language Making computer speech synthesis as natural, flexible, and efficient as human speech.

The CMU Navlab group builds computer-controlled vehicles for automated and assisted driving. Since 1984, we have built a series of robot cars, vans, SUVs, and buses. More recent researches of Navlab ...

I'm a professor in the Machine Learning Department at Carnegie Mellon. I am also affiliated with the Robotics Institute. I'm interested in multi-agent planning, reinforcement learning, ...

I am currently the chair of CATCS . Please check it out - we welcome any suggestions. I was the PC chair of SODA, 2024 . The accepted papers are here. An alternative talk schedule format is here. A ...

Thread operations include thread creation, termination, synchronization (joins,blocking), scheduling, data management and process interaction. A thread does not maintain a list of created threads, nor ...

(This article was written by Bradley Orner, an engineer and former Amway distributor of 3.5 years.) In the past there have been many postings here dealing with the statistics of success in Amway. Here ...

In Nyquist, all functions are subject to transformations. You can think of transformations as additional parameters to every function, and functions are free to use these additional parameters in any ...

`Here!' cried Alice, quite forgetting in the flurry of the moment how large she had grown in the last few minutes, and she jumped up in such a hurry that she tipped over the jury-box with the edge of ...

15-210 aims to teach methods for designing, analyzing, and programming sequential and parallel algorithms and data structures. The emphasis is on teaching fundamental concepts applicable across a wide ...

We introduce a stochastic graph-based method for computing relative importance of textual units for Natural Language Processing. We test the technique on the problem of Text Summarization (TS).

The advent of large-scale training has produced a cornucopia of powerful visual recognition models. However, generative models, such as GANs, have traditionally been trained from scratch in an ...

We introduce the heat method for solving the single- or multiple-source shortest path problem on both flat and curved domains. A key insight is that distance computation can be split into two stages: ...