Amazon Lex launches improved speech recognition models for English

Amazon Lex now offers a neural automatic speech recognition (ASR) model for English that delivers improved recognition accuracy for your voice bots. Trained on data from multiple English locales, the model excels at recognizing conversational speech patterns across diverse speaking styles, including non-native English speakers and regional accents. This reduces the need for end-customers to repeat themselves and improves self-service success rates. To enable this feature, select "Neural" as the speech recognition option in your bot's locale settings.

This feature is available in all AWS commercial regions where Amazon Connect and Lex operate. To learn more, visit the Amazon Lex documentation or explore the Amazon Connect website to learn how Amazon Connect and Amazon Lex deliver seamless end-customer self-service experiences.