Speech Technologies

ANKA Advanced Technologies INC. > Speech Technologies

Automatic Speech Recognition

Speechmatics quality speech technology, combining deep neural networks with decades of experience in speech and software delivery, is unique against our competitors.

Cloud transcription service

Simply upload your audio or video content and receive a full transcript.

Private deployment

ASR technology deployable privately (including on-premises).

Live real-time

Transcribe as you speak with our Real-Time Virtual Appliance.

System integration via an API

Use our API and unlock developer options.

Time Alignment

Provide your transcript with your media file to receive a timestamped document.

Simply upload your video file to get a full, accurate transcript via our cloud transcription service. Our Time Alignment service can then output the word timings of the video.

The Time Alignment service is useful for captioning or archiving video content and making content easily discoverable and searchable online.

Speechmatics’ Automatic Linguist (AL)

AL, our language building framework, uses cutting-edge ASR techniques and machine learning. AL can build any language in the world in as little as a week.

 

A pioneering new theory of how all languages work, AL’s unique framework identifies patterns in global languages, and uses them to automate and generalise tasks across all new language builds.

Requiring minimal data and previous language knowledge, AL’s smart algorithms and cross-build learning make it a fast, accurate and dynamic ASR solution.

 

 

 

PRODUCTS

Batch Virtualised ASR

Our Batch Virtualised ASR provides transcription of pre-recorded audio in a standalone environment provided directly by a virtual machine.

Batch Containerised ASR

Our Batch Containerised ASR provides transcription of pre-recorded audio within a Docker container.

Real-Time Virtual Appliance

Live transcripts provided in ‘real time’. The transcription is provided whilst the input audio is being streamed to the Speechmatics engine.

Private Cloud ASR

Our Private Cloud ASR provides transcription of pre-recorded audio in a standalone environment provided directly by a computer or a virtual machine.

Private Cloud Elastic ASR

Our Private Cloud Elastic ASR provides transcription of pre-recorded audio in a standalone environment provided directly by a computer or a virtual machine.

Cloud Transcription Service

Our Cloud Transcription Service provides transcription of pre-recorded audio from a public cloud operated and managed by Speechmatics.

OUR LANGUAGE COVERAGE

Albanian*

Aymara*

Azerbaijani*

Bashkir*

Basque*

Bengali*

Bulgarian

Catalan

Cebuano*

Central Bicolano*

Chechen*

Croatian

Czech

Danish

Dutch

English GB

English AU

English US

Finnish

French

German

Greek

Guarani*

Haitian Creole*

Hindi

Hungarian

Indonesian*

Ilocano*

Italian

Jamaican Creole English*

Japanese

Javanese*

Kabiyè*

Kannada*

Kazakh*

Korean

Latin*

Latvian

Lithuanian

Malagasy*

Malay*

Malayalam*

Maltese*

Marathi*

Minangkabou*

Mongolian*

Odia*

Oromo*

Pampanga*

Pangasinan*

Persian*

Polish

Portuguese

Quechua*

Romanian

Russian

Somali*

Slovak

Slovenian

Spanish

Sudanese*

Swedish

Tamil*

Tagalog*

Tatar*

Telugu*

Turkish*

Tuvinian Karachay-Balkar*

Udmurt*

Urdu*

Uzbek*

Yoruba Maithili*

*Phase 1