Amazon Lex Benchmark

Amazon Lex is an AWS service that enables developers to build natural language chatbots. For speech inputs, Amazon Lex uses Amazon Transcribe behind the scenes to convert speech to text and then processes the text to understand the user's intent. Lex uses the knowledge learned from sample utterances provided during the training phase to detect the user intent and generate a response.

Prerequisites

• Ubuntu 20.04 (x86_64)
• Git
• Python
• PIP
• AWS Account

Usage

1. Clone the repository:

git clone https://github.com/Picovoice/speech-to-intent-benchmark.git

2. Install the dependencies:

pip3 install -r requirements.txt

3. Log in to AWS console and navigate to Lex console.

4. Use data/amazonlex/barista_432.zip to create and train your bot. The zip file contains a JSON file that defines the barista bot.

5. Run the benchmark:

python3 src/bench.py --engine AMAZON_LEX --noise cafe

python3 src/bench.py --engine AMAZON_LEX --noise kitchen

Result