Speaking of Standards

Today we were very pleased to see the W3C announced that Speech Synthesis Markup Language (SSML) version 1.1 was approved as a Recommendation. The specification is available at:

http://www.w3.org/TR/speech-synthesis11/

SSML is used to control how text is rendered as human-like speech. It includes elements for describing the voice, pitch, speed, and other characteristics of human speech needed to ensure proper output prosody and pronunciation.

Requirements for enhancing SSML 1.0 were collected during workshops held in China, Greece, and India. The new SSML 1.1 W3C recommendation enhances SSML 1.0 to provide better support for a broader set of natural (human) languages.

In particular, SSML 1.1 supports

• a new registry for pronunciation alphabets that describe the pronunciation of words and phrases. Developers use pronunciation alphabets to describe precisely the pronunciations of words and phrases. An example is pinyin, a common way of writing pronunciations for Mandarin Chinese.
• the Pronunciation Lexicon Specification (PLS) to allow for standardized independent collections of pronunciation information that could be also be used by speech recognition engines. (more info about PLS)
• finer author control over voice selection and behavior upon encountering unexpected language content.
• better token delimiting for languages that (1) do not use white space as a token boundary identifier, such as Chinese, Thai, and Japanese, (2) that use white space for syllable segmentation, such as Vietnamese, and (3) that use white space for other purposes, such as Urdu.

Much of the work on this specification took place in China, a country with languages that are quite different from European and American languages. This is the first W3C recommendation in which Asians played a major role.

When published, the final version can be found at http://www.w3.org/TR/speech-synthesis11/.

Voxeo’s own Dan Burnett was a co-editor of the SSML 1.1 specification and contributed this to the W3C’s Testimonials page:

SSML is an important part of the overall ecosystem of W3C standards enabling speech across a variety of applications. SSML in particular provides a key way to render richer, more natural sounding speech. We are particularly pleased that SSML 1.1 provides advancements in several key areas, including support for Asian and Eastern European languages as well as improved audio controls for authors. The headway in the Recommendation is the result of the work of the dedicated individuals and companies around the world who value the importance of standards work and support the W3C Voice Browser Working Group. Voxeo is very proud to have been involved in this significant global accomplishment.

We’re pleased to see SSML 1.1 reaching this milestone and congratulate all involved.

As I’ve written about previously, the Media Resource Control Protocol (MRCP) is currently undergoing revision within the IETF to arrive at a new “MRCPv2″. Voxeo’s Dan Burnett has been editing the draft specification to incorporate the latest rounds of comments and last month released the 20th revision of the Internet-Draft:

http://tools.ietf.org/html/draft-ietf-speechsc-mrcpv2

If you aren’t familiar with MRCP, it’s a protocol that allows products such as our Prophecy platform to easily interoperate with Automatic Speech Recognition (ASR) or Text-To-Speech (TTS) engines. You can think of it like this:

With MRCP, your application platform can connect to any “MRCP-compliant” speech engine. It’s an open standard that we certainly like because it unlocks our platform and lets you use any of the great number of speech engines supported by Prophecy. We’ve also had customers approach us in the past about using special speech engines – and the open interface of MRCP provides the way in which this can happen.

In any event, MRCPv2 is moving closer to completion – if you have any comments about the latest draft, now is a really good time to send them in to the editors.

At SpeechTEK in New York City a few weeks ago, our own Dan Burnett was recognized by Speech Tech Magazine as one of the “2008 Speech Luminaries” for all his years of work on industry standards relating to speech. We were delighted for Dan to receive the (well-deserved!) recognition and I had a chance to record a brief video interview with Dan at SpeechTEK:

As Dan mentions, he is Director of Speech Technologies in our Office of the CTO (OCTO) reporting in to our CTO, RJ Auburn, and is responsible for looking at how to constantly improve our speech recognition technology and also ensure it is compliant with standards.

Congratulations, Dan, on the recognition by Speech Technology Magazine!

---

P.S. And yes, for those following along at home, Dan Burnett and I were both hired into the OCTO at about the same time… we thought about instituting a rule where all new OCTO employees had to be named “Dan”, but thankfully that rule was ignored with the recent excellent addition of Wei Chen!

Technorati Tags: voxeo, dan burnett, standards, w3c, voicexml, mrcp, speech, speechtek, speechtek2008