Speech Segmentation and Labeling on the NeXT Machine

TitleSpeech Segmentation and Labeling on the NeXT Machine
Publication TypeTechnical Report
Year of Publication1990
AuthorsWooters, C., & Morgan N.
Other Numbers566

We are attempting to incorporate connectionist models into speech recognition algorithms. Since these models require a large amount of training data, it was necessary to build an automated speech labeling/segmentation application. There were two significant system requirements for this program:Digital-to-analog capabilities.Support for speedy development of applications requiring a user-interface.The NeXT machine fulfills both of these requirements. It has built in AD/DA capabilities. Its object-oriented programming environment and application-building modules permit quick program development.We report here on a program we have developed to integrate automatic labeling and segmentation of continuous speech with a manual system for observing and correcting these signal annotations. The overall system has functioned well enough to permit easy user marking of 600 sentences in a reasonable amount of time.

Bibliographic Notes

ICSI Technical Report TR-90-002

Abbreviated Authors

C. Wooters and N. Morgan

ICSI Publication Type

Technical Report