EchoSense AI – Contrastive Speech Analytics

Inspiration

Communication is an important part of everyday life, but people may not always recognize differences in their speaking patterns. We were inspired to build EchoSense-AI to make speech analysis easier through artificial intelligence and audio processing.

What it does

EchoSense-AI analyzes and compares two speech recordings: ideal speech and flawed speech. It extracts speech characteristics such as speaking rate, pitch, energy, and pauses, and provides visual comparisons to help users understand the differences.

How we built it

We built EchoSense-AI using Python and Streamlit. We integrated audio-processing techniques, speech transcription, feature extraction, and a dashboard to display analysis results.

Challenges we faced

One of our main challenges was processing audio recordings reliably and ensuring the required tools worked in the cloud deployment environment. We worked on audio processing, transcription, and displaying meaningful comparison results through the dashboard.

What we learned

We learned how to combine speech processing, AI-based transcription, data analysis, and web application development into a single project. We also gained experience deploying and testing an application in a cloud environment.

What's next

We plan to improve the accuracy of speech comparisons, enhance the visualizations, and explore additional features that can help users better understand and improve their speaking patterns.Inspiration

What it does

How we built it

Challenges we ran into

Accomplishments that we're proud of

What we learned

What's next for EchoSense AI – Contrastive Speech Analytics

Built With

• artificial
• ffmpeg
• librosa
• numpy
• openai-whisper
• python
• scikit-learn
• scipy
• speech-processing
• streamlit