Wireless RERC - Text-to-Speech (TTS)

Georgia Tech Creates Google Glass Caption Software

mz22 — Fri, 17 Oct 2014 15:36:59 +0000

Researchers create software for Google Glass that provides captions for hard-of-hearing users

October 2014 – A research team at Georgia Tech has created Google Glass speech-to-text software that facilitates conversations for users who are hard-of-hearing. The software allows people who are hard-of-hearing to wear Google Glass while another person speaks into a smartphone. The smartphone works with an Android transcription API, allowing the speech to be converted to text and displayed on Glass’ heads-up display.

The software was inspired by Georgia Tech’s School of Interactive Computing Professor, Jim Foley. When asked about the software, Foley said, “This system allows wearers like me to focus on the speaker’s lips and facial gestures. If hard-of-hearing people understand the speech, the conversation can continue immediately without waiting for the caption. However, if I miss a word, I can glance at the transcription, get the word or two I need and get back into the conversation.”

The captioning software for Google Glass is available for download at MyGlass. For more information about the project, please click the here.

Making Emergency Information Accessible

mz22 — Wed, 19 Dec 2012 14:34:15 +0000

Emergency Information

Twenty-First Century Communications and Video Accessibility Act of 2010 (CVAA)

Text-to-Speech (TTS)

Vision Loss

Comments of the Wireless RERC

Publication Type:

Policy Filings

The Wireless RERC filed comments with the Federal Communications Commission (FCC) in response to their Notice of Proposed Rulemaking In the Matter of Accessible Emergency Information, and Apparatus Requirements for Emergency Information and Video Description: Implementation of the Twenty-First Century Communications and Video Accessibility Act of 2010. The comments highlighted research findings of the Wireless RERC concerning the accessibility of emergency alerts, including that people with vision loss consistently encounter challenges in accessing the content of emergency information when there is no audio version of the on-screen information. Though the Wireless RERC endorsed the use of text-to-speech (TTS) technology to provide simultaneous audio of the text crawl, we recommended that the TTS be required to be of high quality to ensure that the audio information is clear and understandable. In order to provide guidance on TTS quality, we recommended that the Video Programming Accessibility Advisory Committee (VPAAC) be tasked with identifying and examining extant standards on the provision of TTS to determine quality assurance parameters.

Additionally, Wireless RERC comments addressed the use of abbreviations, describing non-text emergency information such as maps, alternate means of compliance, and the policy implications of live IP-delivered programming.

FCC Reconsiders Text-to-Speech for EAS

blippincott4 — Tue, 01 May 2012 19:13:28 +0000

FCC

Federal Emergency Management Agency (FEMA)

Commercial Alert Protocol (CAP)

Emergency Alert System (EAS)

Order on Reconsideration

04.19.12 – The FCC issued an Order on Reconsideration “In the Matter of Amendment of the Review of the Emergency Alert System” [EB Docket No. 04-296] reconsidering the Commission’s rules on the use of text-to-speech (TTS) by Emergency Alert System (EAS) participants. On January 10, 2012, the FCC released a Fifth Report and Order which required EAS participants to convert and process CAP messages into a format outlined in the EAS-CAP Industry Group’s (ECIG) Implementation Guide. However, at the time, the rules barred the use of TTS technology when the CAP message does not include an audio file, noting that “accuracy and reliability of TTS had not been established in the record.” Following a “Petition for Reconsideration,” filed by the Federal Emergency Management Agency (FEMA), which stated that a lack of TTS could lead to possible disruptions of National Weather Service alerts or a lack of information for subscribers, and similar filings from stakeholders, the FCC has revised section 11.56(a)(2) of the rules and will allow EAS participants to adhere to the TTS specifications included in the ECIG Implementation guide on a voluntary basis. This reconsideration will become effective immediately upon publication in the Federal Registrar. [Source: FCC]