Machine Learning

Artificial Intelligence

Voice Assistant

Naturallanguageprocessing

Speech Recognition

Explore recommended reads, summarized by AI

Building Systems

Technical guides and discussions on developing, deploying, and improving speech recognition technology.

Domain Adaptation and Language Modeling

System Development and Applications

Whisper Implementation and Optimization

Voice Interfaces

Projects and tutorials for creating voice-enabled assistants, chatbots, and conversational AI applications.

Voice Assistant Projects

Popular this week

Pop Alexandru

NVIDIA Just Released a 34B Speech Model That Only Activates 4.3B Parameters

Md Rasul Islam Bapary

State Space Models and Mamba, from First Principles

Kowshik T G

One Model, Two Worlds: Inside NVIDIA’s Nemotron-Labs-Unified-ASR-0.6B

Saad Naeem

Running Whisper large-v3-turbo in a Browser Tab: Urdu Speech to Text With No Server

Kyrylo Shchupii

How I Built Our Own Call Recorder (and What Went Wrong Along the Way)

Latest stories

In

Open Intelligence

by

Dr. Fadi Shaar

Speak Instead of Type: How Hex Brings Private, Local Voice Dictation to Every App

Yuktha

Five Ways to Represent the Same Speech: A Developer’s Guide to Saaras V4

In

Neural Notions

by

VoxRT

Model compression trade-offs for streaming voice AI

kaleem

Offline Dictation on Windows and Mac: How to Set It Up and Prove It Works With Wi-Fi Off

Sarathc

How Are Speech and Audio Language Model Benchmarks and RL Datasets Built?

See more stories

Who to follow

Popular this week

Pop Alexandru

NVIDIA Just Released a 34B Speech Model That Only Activates 4.3B Parameters

Md Rasul Islam Bapary

State Space Models and Mamba, from First Principles

Kowshik T G

One Model, Two Worlds: Inside NVIDIA’s Nemotron-Labs-Unified-ASR-0.6B

Saad Naeem

Running Whisper large-v3-turbo in a Browser Tab: Urdu Speech to Text With No Server

Kyrylo Shchupii

How I Built Our Own Call Recorder (and What Went Wrong Along the Way)

Latest stories

In

Open Intelligence

by

Dr. Fadi Shaar

Speak Instead of Type: How Hex Brings Private, Local Voice Dictation to Every App

Yuktha

Five Ways to Represent the Same Speech: A Developer’s Guide to Saaras V4

In

Neural Notions

by

VoxRT

Model compression trade-offs for streaming voice AI

kaleem

Offline Dictation on Windows and Mac: How to Set It Up and Prove It Works With Wi-Fi Off

Sarathc

How Are Speech and Audio Language Model Benchmarks and RL Datasets Built?

See more stories

Who to follow