Voice Word Accuracy Rates Improving Rapidly... +90% Accuracy for Major Platforms Word Accuracy Rates by Platform*, 2012 – 2016 *Word accuracy rate definitions are unique to each company...see footnotes for more details 100% 90% 80% ) % ( 70% e at 60% R acy 50% r 40% ccu A 30% d r 20% o W 10% 0% Baidu1 Google2 Hound Voice Search3 (2012 - 2016) (2013 - 2015) & Assistant App (2012 - 2016) Source: Baidu, Google, VentureBeat, SoundHound Note: *Word Error Rate (WER) definitions are specific to each company. Word accuracy rate = 1 - WER. (1) Data shown is word accuracy rate on Mandarin speech recognition on one of Baidu's speech tasks. Real world mobile phone speech data is very noisy and hard for humans to transcribe. A 3.5% WER is better than what most native speakers can accomplish on this task. WER across different KPCB INTERNET TRENDS 2016 | PAGE datasets and languages are generally not comparable. (2) Data as of 5/15 and refers to recognition accuracy for English language. Word error rate is evaluated using real world search data which is extremely diverse and more error prone than typical human dialogue. (3) Data as of 1/16 and refers to recognition accuracy for English language. Word accuracy rate based on data collected from 119 thousands of speakers and real world queries with noise and accents.