SpinVox Focuses on Technology
- Sunday, July 26th, 2009
- Share this article:
SpinVox has followed up its blog response to allegations made by the BBC last week, which it described as both incorrect and inaccurate with a statement about its technology.
Over the weekend, the company, in its own words, took the opportunity to reveal some of the details about the technological breakthroughs it has achieved in the development of its Voice Message Conversion System (VMCS).
Though not couched as a direct response to the allegations made by the BBC last week, the statement cleary is. It describes the core technology around which the VMCS is built, saying that it is based on world-leading breakthroughs in automatic speech recognition (ASR) combined with artificial intelligence, semantics and natural linguistics which have been developed by SpinVox's Cambridge-based Advanced Speech Group (ASG).
The statement says that VMCS already knows more than 99% of anything a user is likely to say, and that it contains over 2 billion words and phrases derived from the equivalent of 72 years of audio training. Dr Tony Robinson and the SpinVox ASG of more than 20 speech specialists and PhDs are working continually to develop and refine the system. The group of technologies and processes within the VMCS, says SpinVox, are the main engine for converting voice messages to text, rather than human intervention.
The statement then goes on to say that SpinVox realised that only by combining its rapidly technology with human quality control and training could it create a system which could complete elements of messages which could not be automatically converted.
Quality Control agents are an important part of the SpinVox service because their constant minute-by-minute input actually improves the quality of text conversions in a process we call `live learning` explains SpinVox CIO Rob Wheatley. The technology is a bit like a human brain, in that, the more it is exposed to input, the more it learns.
Wheatley goes on to say that the system now requires only 2% of the input it required just two years ago and can now predict more than 99% of what most people speaking in English or Spanish will say next. As a result, Wheatley says that SpinVox has reduced the requirement for human intervention to just a few hundred agents per market compared to the thousands per market when we started.
The statement says that every message is dealt with initially by the automated system. Only in cases where speech is too indistinct to be dealt with by the system, or contains unfamiliar or new words or phrases, is the completely anonymised and encrypted message sent to a QC agent for help. The agents will only ever see the messages that need input and do not know how many other messages have been converted, processed and sent automatically by VMCS.
The statement also says that SpinVox is fully compliant with industry standards relating to the processing of information, including the Data Protection Act 1998. To this end, any part of a message seen by the Quality Control centres is anonymous, encrypted and randomised, meaning that it is impossible to determine where the messages are from or where they are going to. SpinVox notes that it has achieved two ISO qualifications: ISO 27001 (the international Information Security Standard) and ISO 9001:2008 quality certification.
It also quotes Jaime Tronqued, President of ScopeWorks Asia, Inc., a Quality Control house that has worked with SpinVox for the past two years, who says:
I can categorically assure people that SpinVox messages are both private and secure. There are many layers of security and privacy that are used to ensure this and SpinVox was extremely thorough in its audit of our operations, our security and our privacy procedures as they ran a training pilot with our Quality Control agents on test conversion messages, prior to contracting with us to deliver a live customer service using encrypted and anonymised messages.
This is a story that looks set to run for some time yet.