Biometric voice and speech recognition

Biometric voice and speech recognition

Voice Recognition or Speech Recognition?

Voice and speech recognition are two separate biometric modalities that, because they are dependent on the human voice, see a considerable amount of synergy. Both are contactless, software-based technologies, and as such are counted among the most convenient biometrics in regular use. The first step to understanding this kind of biometrics is to make the key distinction between voice and speech recognition. A system's ability to process "what a person is saying" - and speaker verification, "technology based on individual vocal physiology and behavior to validate a claim of identity." In fact, speech recognition is a user interface technology that by measuring the sounds a user makes while speaking can measure the unique biological factors that, combined, produce her voice. According to an Unisys survey, the biometric measures ranked by consumer preference are voice recognition (32%), fingerprints (27%), facial scan (20%), hand geometry (12%), and iris scan (10%). This ranking seems to confirm that people prefer convenience and familiarity when choosing a biometric technology.

In today's increasingly mobile and connected world, having hands-free interface options is critical. Voice recognition technology also called voice command, allows users to interact with and control technologies by speaking to them. Speech recognition technologies are changing the world around us. With the rise of the internet of things, voice recognition is finding a niche. Always on speech recognition is making today's mobile devices easier to use than ever before. Speech technologies are creating amazing opportunities for today's organizations and are strengthening other biometric login solutions.

How do speech and voice recognition work?

Voice recognition technology is possible after making a digital model of an individual's voice that can serve as a stored profile or template of that voiceprint. Words and phrases are broken down into various kinds of frequency patterns that, taken together, describe someone's unique way of speaking. The templates are stored in databases for matching like other kinds of biometric data.

These systems can be text-dependent or text-independent (and sometimes a combination) and used, for example, to control access and time & attendance. For the first option, numbers or phrases can become spoken passwords that can be compared to a sample of those same words that were acquired during enrolment. Text independent technology does not require a passphrase but analyzes the speaker's free speech for unique vocal characteristics.

Practical applications of speech recognition

  • All voice and speech recognition needs are a microphone to listen. Chances are you have voice recognition on your personal mobile device. Each of Microsoft’s Cortana and Android’s OK Google can perform searches and basic tasks based on voice command.
  • When it comes to protecting physical access, speaker verification can be used, for instance, to log warehouse employees with voice data collection systems as they move about an environment during work. Speech verification combined with GPS is also being used to keep track of security guards to make sure they are making their rounds, and not relying on friends to do it for them.
  • The USAA banking app, for example, uses facial recognition and voice recognition to provide easy and secure multi-factor biometric security, the voice component adding an extra level of liveness detection to the process.
  • Since all types of biometric applications on the rise, voice-based authentication is one approach that seems to engender less resistance among users than other biometric forms of security. Voice recognition is non-contact, non-intrusive, and easy to use.
  • Voice recognition for authentication is increasingly being found in call centers. Swisscom, one of Switzerland’s biggest telecoms, recently implemented voice recognition in its call centers.

Challenges with speech recognition

Variety challenges affect its accuracy. These include poor-quality voice samples. The variability in a speaker's voice due to illness, mood, and changes over time; background noise as the caller interacts with the system; and changes in the call's technology (digital vs. analog, upgrades to circuits and microphones, etc.)

Related Posts