rSpeak Technologies is proud to announce that rSpeak’s American English female voice Sophie has been recognised by long-time speech industry observer ASR News as the most accurate text-to-speech voice available on the market.
In their freshly released, 2016 Text-to-Speech Accuracy Testing report, ASR News presented the accuracy performance of commercially available Text-to-Speech (TTS) products. Using a test corpus of over fifteen hundred phrases, each unit was tested, scored and results tabulated.
The test corpus (1,589 words/phrases) was segmented into categories which included: Number Handling; Homograph Handling; Handling of Words of Foreign Origin; Acronym Handling; Abbreviation Handling; Name Handling; and Address Handling and the test results were presented in these categories. The average score for all units tested was 79.2% correct. Overall scores ranged from 55.3% to 98.6% correct.
Among the 12 TTS products tested, representing the text to speech vendors’ latest available releases, rSpeak Technologies stole the show with an outstanding overall accuracy rate of 98.6!
rSpeak Technologies’ unique combination of text normalization, lexical lookup, grapheme to phoneme modelling, prosody modelling, manuscript creation, recording of voice talent and acoustic database creation ensures that the outstanding, lifelike quality of our TTS voices enhance the customer experience across all verticals.