17644147. DETECTION OF COGNITIVE IMPAIRMENT USING SPEECH FEATURE DISTRIBUTION simplified abstract (INTERNATIONAL BUSINESS MACHINES CORPORATION)

From WikiPatents
Jump to navigation Jump to search

DETECTION OF COGNITIVE IMPAIRMENT USING SPEECH FEATURE DISTRIBUTION

Organization Name

INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor(s)

Kaoru Shinkawa of Hachioji-shi (JP)

YASUNORI Yamada of Kawaguchi-Shi (JP)

MASATOMO Kobayashi of Tokyo (JP)

DETECTION OF COGNITIVE IMPAIRMENT USING SPEECH FEATURE DISTRIBUTION - A simplified explanation of the abstract

This abstract first appeared for US patent application 17644147 titled 'DETECTION OF COGNITIVE IMPAIRMENT USING SPEECH FEATURE DISTRIBUTION

Simplified Explanation

The patent application describes a method, computer system, and computer program for analyzing speech features. Here are the key points:

  • The invention involves receiving multiple speech samples from a user.
  • The speech samples are divided into several pause segments.
  • The duration of each pause segment is determined.
  • The distribution of pause durations is analyzed.
  • The distance between the distributions of pause durations is calculated.

Potential applications of this technology:

  • Speech recognition systems: The analysis of pause durations can improve the accuracy of speech recognition by providing insights into natural speech patterns.
  • Speaker identification: The distribution of pause durations can be used as a unique identifier for different speakers.
  • Language learning: Analyzing pause durations can help identify patterns and improve pronunciation and fluency.

Problems solved by this technology:

  • Inaccurate speech recognition: By considering pause durations, the system can better understand the intended words and improve recognition accuracy.
  • Speaker confusion: The analysis of pause durations can help distinguish between different speakers, reducing the chances of misidentification.
  • Language learning difficulties: Analyzing pause durations can provide valuable feedback to language learners, helping them improve their speaking skills.

Benefits of this technology:

  • Improved speech recognition accuracy: By considering pause durations, the system can better understand the context and improve recognition accuracy.
  • Enhanced speaker identification: The analysis of pause durations can provide a more reliable and unique identifier for different speakers.
  • Effective language learning: Analyzing pause durations can provide valuable feedback to language learners, helping them improve their pronunciation and fluency.


Original Abstract Submitted

A method, computer system, and a computer program product for speech feature distribution is provided. The present invention may include receiving two or more speech samples from a user. The present invention may include dividing the two or more speech samples into a a plurality of pause segments. The present invention may include determining a pause duration for each of the plurality of pause segments. The present invention may include determining a distribution of pause durations. The present invention may include determining a distance between the distribution of pause durations.

Retrieved from "http://wikipatents.org/index.php?title=17644147._DETECTION_OF_COGNITIVE_IMPAIRMENT_USING_SPEECH_FEATURE_DISTRIBUTION_simplified_abstract_(INTERNATIONAL_BUSINESS_MACHINES_CORPORATION)&oldid=26211"