Phonexia Keyword Spotting (KWS) technology automatically identifies the occurrences of specific keywords and keyphrases in audio recordings.
Identify the topics of calls and audio recordings automatically based on the appearance of specific keywords and keyphrases in the speech.
Cut through large amounts of audio recordings quickly with the automatic detection of spoken keywords and find what you need faster.
Ensure that voicebots can quickly understand the context of the given voice command by checking for appropriate keywords in the speech.
Technology Details
• Uses the robust acoustic-based approach applicable even in noisy environments
• Keywords are automatically converted into phonemes and searched for
• Applies state-of-the-art channel compensation techniques compatible with the broadest range of audio sources possible: GSM/CDMA, 3G, VoIP, landlines, satellite phones, etc.
• Users can add an unlimited number of keywords and pronunciation variants for each keyword
• WAV or RAW (PCM unsigned 8 or 16 bits, IEEE float 32-bit, A-law or Mu-law, ADPCM), FLAC, OPUS; 8 kHz+ sampling (other audio formats are automatically converted)
• List of keywords
• XML/JSON format with all results
• Results files containing details about the detected keywords (keyword, start/end time, path, probability, etc.)
5th Generation:
Czech, Dutch, English US, Polish, Russian, Slovak, Spanish – Latin American
4th Generation:
Arabic, Chinese, Croatian, Farsi, French, German, Hungarian, Italian, Pashtu, Turkish
• The 5th generation is approximately 30x faster than real-time processing on 1 CPU core—for example, a standard 8 CPU core server processes 5,760 hours of audio in one day of computing time
• The 4th generation is approximately 10x faster than real-time processing on 1 CPU core—for example, a standard 8 CPU core server processes 1,920 hours of audio in one day of computing time
Schedule a demo with our experts and see for yourself how Phonexia Keyword Spotting technology can help your business.
We will show you a free online demo tailored to your needs, showcasing Phonexia speech and voice recognition technologies and the ways you can use them to achieve your project’s goals.
