Amazon Lex launches improved speech recognition models for English
News
This article announces improved speech recognition models for Amazon Lex, featuring a new neural ASR model for English that enhances voice bot accuracy.
- Neural ASR model trained on multiple English locales for better accuracy
- Recognizes conversational speech patterns across diverse speaking styles
- Handles non-native English speakers and regional accents effectively
- Reduces customer repetition and improves self-service success rates
- Enable by selecting "Neural" option in bot locale settings
- Available in all AWS commercial regions with Amazon Connect and Lex
Amazon Lex's new neural speech recognition model improves voice bot accuracy and customer experience by better understanding diverse English speakers and accents.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
Dec 11
2024
2024
Amazon Lex launches new multilingual speech recognition models
Jan 12
2026
2026
Amazon Lex launches configurable voice activity detection sensitivity
Nov 26
2025
2025
Amazon Lex now supports LLMs as the primary option for natural language understanding
Sep 16
2025
2025
Amazon Lex provides generative AI based enhanced natural language understanding in eight new languages
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.