Publication Details
Title: Speech Segmentation and Labeling on the NeXT Machine
Author: C.Wooters and N. Morgan
Group: ICSI Technical Reports
Date: January 1990
PDF: http://www.icsi.berkeley.edu/pubs/techreports/tr-90-02.pdf
Overview:
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 Information:
ICSI Technical Report TR-90-002
Bibliographic Reference:
C.Wooters and N. Morgan. Speech Segmentation and Labeling on the NeXT Machine. ICSI Technical Report TR-90-002, January 1990
Author: C.Wooters and N. Morgan
Group: ICSI Technical Reports
Date: January 1990
PDF: http://www.icsi.berkeley.edu/pubs/techreports/tr-90-02.pdf
Overview:
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 Information:
ICSI Technical Report TR-90-002
Bibliographic Reference:
C.Wooters and N. Morgan. Speech Segmentation and Labeling on the NeXT Machine. ICSI Technical Report TR-90-002, January 1990