Speech-to-Text

Ear-machine

We developed Ear-machine using most advanced deep learning neural network algorithms for automatic speech recognition (ASR).

Ear-machine convert your voice into text (data) at state-of-the-art accuracy. Ear-machine can be applied as voice processing core technology for many purposes.

AI

Ear-machine using most advanced deep learning neural network algorithms.

High accuracy

Ear-machine convert your voice into text (data) at state-of-the-art accuracy.

Regional accent

Ear-machine is optimized with multi-regional voices (north, south and central)

Frequently update

Frequently update to ensure Ear-machine covers 100% of Vietnamese vocabulary.

Noise robustness

Ear-machine can handle noisy audio from many environments without requiring additional noise cancellation.

Realtime converting

Receive real-time speech recognition results as Ear-machine can process at realtime mode.

Audio format flexibility

Ear-machine can process any audio format. It facilitates the integration with customer's system.

Integration

Deploy speech recognition wherever you need, whether in the cloud with the API or on-premises.

Regional accent
Domain-specific models
Process at realtime mode (less than 500ms)
Updated by thousands hour of data

About Dinosoft

Dinosoft was founded by experts in the field of artificial intelligence. Dinosoft specialied in R&D of artificial intelligence applications in the fields of Vietnamese speech recognition, speech synthesis and machine translation. Our solutions apply many technologies and in-depth knowledge in the fields of: language, signal processing, acoustics physics, computer science... to give customers the ability of automating the voice-related processes. For more information about our solutions, please contact:

Dinosoft Jsc.
info@dinosoft.vn