Melvyn J. Hunt

TL;DR: In this article, a system and processes for detecting and/or providing a whispered speech response are provided, where speech is received from a user, and based on the speech input, determined that a whispering speech response is to be provided.

TL;DR: In this paper, an energy change of each frame making up signals including speech and non-speech signals is detected and a speech segment corresponding to frames that include only speech signals from among the frames based on the detected energy change.

TL;DR: Apple’s hybrid unit selection speech synthesis system, which provides the voices for Siri with the requirement of naturalness, personality and expressivity, is described and various techniques that enable on-device capability such as preselection optimization, caching for low latency, and unit pruning for low footprint are described.

TL;DR: In this article, a system and method of speech recognition involving a mobile device is described, where a set of phonetic symbols are converted to speech input and data relating to the symbols is transferred from the mobile device over a communications network to a remote processing device, where it is used to identify at least one matching data item.

TL;DR: A novel approach to the problems of topic and speaker identification that makes use of a large vocabulary continuous speech recognizer and describes the symmetric way in which it has implemented their solution.