Go to Top
Web Icon - Avanzada 7

A maximum of 3 products can be compared. Please, unselect any of them.

VERBIO ASR on-line monolingual

  • Imagen 1: VERBIO ASR on-line monolingual
  • Imagen 1: VERBIO ASR on-line monolingual

Avanzada 7 code: 0040430270053

Manufacturer SKU: AP-2901

Producto descatalogado

  • Verbio ASR is VERBIO's speech recognition engine. Aimed at telephone applications, and speaker-independent, it is also applicable in certain microphone and multimedia applications. Available in the different languages used in the Iberian peninsula and in most Latin American countries.

    Automatic Speech Recognition (ASR) is a technology that allows users to automatically convert a natural spoken speech into a text that corresponds to the speech with the maximum possible precision. It allows any system that incorporates this engine to "understand" or interpret the contents of a speech, regardless of the speaker’s voice.

    • A system able to understand any person with great precision, thanks to a design created from voice databases of thousands of people per language, selected in accordance with strict geographic and demographic criteria. This is why it is speaker-independent.
    • Several languages: recognition in Spanish, Catalan, Basque, Galician and other international lingua franca such as English; French(*); European and Brazilian Portuguese; Mexican, Argentinean, Chilean, Venezuelan and most other Latin American variants of Spanish. Multilingual system that can be used in various languages simultaneously.
    • Acoustic modelling with special features for telephone voice, and, especially, for GSM mobile telephony (which, in practice, is more widely used than fixed telephony), where it stands out thanks to its robust protection against background noise.
    • Verbio ASR also offers a system with a semantic interpretation of the result, which means that the error rates are very low, and allow the parametrisation of the development of the voice applications or dialogues, increasing the possibilities for development of natural dialogues.
    • Most common specific basic recognition grammars already incorporated, such as: digit sequences, spelling, yes/no, dates, times, identity document numbers, credit cards and telephone numbers.
    • Possibility of direct integration with a speaker identification system, with Verbio Speaker ID.

     

    The voice synthesis engine Verbio TTS is especially indicated for issuing messages in the interaction between man and machine and personal communications in environments such as:

    • Telephony and CTI: Call centres, IVRs, unified Messaging, Automatic operators, Voice portals, etc.
    • Multimedia: Carrying out prototypes, CDs of generic changing information, catalogues, presentations, etc.
    • Internet: Personalised messages in web pages, with last-minute information voice messages, reminders, spoken help instructions, e-mail or news readings, etc.
    • Domotics: Confirmation of information or reading of system data.
    • Disabilities: Help and support applications for different degrees of disabilities, verification of information or commands.
    • Industrial: Help in the industrial automation of processes by voice (logistics, machinery, etc).
    • Multimedia terminals (mobiles, PDAs, etc.): Listening to information on mobiles on hands free mode, listening to information or data confirmation.

Related products