SISCOM provides innovative telephony solutions and applications in speech technologies in different languages of English, French and Arabic. We mean by speech technology: Automatic speech recognition (ASR), speech authentication and text-to-speech (TTS).
Automatic speech recognition is the process by mapping an acoustic speech signal to text. Automatic speech understanding is a process in mapping an acoustic speech signal to some form of abstract meaning of the speech.
Telephony applications and solutions are speaker independent which is restricted to list of word commands (isolated word, limited vocabulary) to make things easier.
SISCOM provides top end speech technologies in Arabic languages including different accents in models of fluent and slang. There are list of tools that manage the rules, grammars and pools of words which gives the speech recognition maturity very close to human responses.
Speech Authentication (Speaker Recognition)
Speech authentication or speaker recognition is the process of automatically recognizing who is speaking based on individual information included in speech signals. It can be divided into speaker identification and speaker verification.
Speaker identification determines which registered speaker provides a given utterance from amongst a set of known speakers. Speaker verification accepts or rejects the identity claim of a speaker.
This technology overlaps with the biometrics industry. It enables access to restricted services using voice as the means of authentication, which is considered more secure and convenient than traditional methods like passwords, PINs, smart cards etc.
Text-To-Speech (Speech Synthesis)
Speech synthesis is the process of converting textual input to spoken output by automatically generating synthesized speech.