Breaking News

Samsung Galaxy S25 Edge Features New Corning Gorilla Glass Ceramic 2 for Enhanced Durability Razer announces Clio Chair Accessory for Audio Immersion Razer Unveils Ergonomic Gaming Mouse and Keyboard for Gaming on the Go Noctua releases NH-D15 G2 specific offset LGA1851 mounting bars for improved cooling performance ADATA Launches T7 and T5 Enterprise SSD Series

logo

  • Share Us
    • Facebook
    • Twitter
  • Home
  • Home
  • News
  • Reviews
  • Essays
  • Forum
  • Legacy
  • About
    • Submit News

    • Contact Us
    • Privacy

    • Promotion
    • Advertise

    • RSS Feed
    • Site Map

Search form

Toshiba's Voice Recognition Technology Can Distinguish Multiple Individual Speakers Without Training

Toshiba's Voice Recognition Technology Can Distinguish Multiple Individual Speakers Without Training

Enterprise & IT Oct 25,2016 0

Toshiba has developed a technology capable of precisely distinguishing the voices of individual speakers in real time, even when multiple persons are speaking at the same time.

Typically, voice recognition reliability falls off when multiple people speak simultaneously. While technologies have been developed for separating simultaneous speech, the acoustic characteristics of locations where conversations take place and recording environment factors, such as the positioning of the speakers, have required provision of dozens of minutes of recordings to realize training for optimal separation.

Toshiba claims that its new technology achieves precise, real-time identification of speakers and separate voice capture, even when many voices are trying to be heard, and delivers high-precision recognition and transcription of each speaker, using a microphone array embedded in a single sound input device.

High-precision transcription alleviates the need for manually keeping minutes in business meetings, and allows an increased focus on analysis of customer opinions and the improvement of staff manuals. Transcriptions of meetings with customers from overseas can also be used for automatic translation systems.

A problem with previous sound-source separation systems is that they require many minutes of pre-recorded speech for system training in order create a sufficiently precise separation filter for each speech source (person). Toshiba's method replaces this time-consuming direct learning for filter creation with learning of the spatial characteristics representing speaker position information from the positioning of the microphones. This achieves high-performance separation supported by continuous filter updates according to the environment, and approximately double the separation precision of previous techniques. Toshiba says that when separating simultaneous speech of two speakers, the amount of suppression of the of the second person's speech was improved from 3 to 9 dB - an approximate doubling.

In operation, the new system rapidly determines the relative positioning of speakers through matching an association table for sound direction to the time difference at which sound arrives from speakers attached to each microphone. This technique allows the capture and separation of each individual's voice, even when there are simultaneous utterances and without any previous recordings at the location.

Toshiba keeps working on the new technology, and plans to include it to its 2017 RECAIUS cloud-based service that supports various human activities for understanding the intentions of humans in audio and visual recordings.

Tags: Toshiba
Previous Post
Emporio Armani Launches A Hybrid Smartwatch
Next Post
Alexa Skill To Lets You Control Your Harmony Hub-based Universal Remotes

Related Posts

  • Toshiba expands storage evaluation services in EMEA with new HDD Innovation Lab

  • Toshiba Unveils New Canvio Flex and Canvio Gaming 2.5” Portable Hard Drives

  • Toshiba Collaborates with PROMISE Technology on Providing the Optimal Data Storage Technology for CERN’s Large Hadron Collider

  • Toshiba Announces 24TB CMR and 28TB SMR Enterprise Hard Disk Drives

  • Toshiba Canvio Flex 4TB

  • Toshiba Canvio Basics 1TB

  • Toshiba’s next-generation S300 Pro Surveillance HDDs for large-scale video surveillance systems

  • Toshiba Announces MG10-D Series of Enterprise HDDs with Capacities up to 10TB

Latest News

Samsung Galaxy S25 Edge Features New Corning Gorilla Glass Ceramic 2 for Enhanced Durability
Smartphones

Samsung Galaxy S25 Edge Features New Corning Gorilla Glass Ceramic 2 for Enhanced Durability

Razer announces Clio Chair Accessory for Audio Immersion
Consumer Electronics

Razer announces Clio Chair Accessory for Audio Immersion

Razer Unveils Ergonomic Gaming Mouse and Keyboard for Gaming on the Go
PC components

Razer Unveils Ergonomic Gaming Mouse and Keyboard for Gaming on the Go

Noctua releases NH-D15 G2 specific offset LGA1851 mounting bars for improved cooling performance
Cooling Systems

Noctua releases NH-D15 G2 specific offset LGA1851 mounting bars for improved cooling performance

ADATA Launches T7 and T5 Enterprise SSD Series
Enterprise & IT

ADATA Launches T7 and T5 Enterprise SSD Series

Popular Reviews

be quiet! Light Loop 360mm

be quiet! Light Loop 360mm

be quiet! Dark Rock 5

be quiet! Dark Rock 5

G.skill Trident Z5 Neo RGB DDR5-6000 64GB CL30

G.skill Trident Z5 Neo RGB DDR5-6000 64GB CL30

Arctic Liquid Freezer III 420 - 360

Arctic Liquid Freezer III 420 - 360

Crucial Pro OC 32GB DDR5-6000 CL36 White

Crucial Pro OC 32GB DDR5-6000 CL36 White

be quiet! Dark Mount Keyboard

be quiet! Dark Mount Keyboard

be quiet! Light Base 600 LX

be quiet! Light Base 600 LX

Crucial T705 2TB NVME White

Crucial T705 2TB NVME White

Main menu

  • Home
  • News
  • Reviews
  • Essays
  • Forum
  • Legacy
  • About
    • Submit News

    • Contact Us
    • Privacy

    • Promotion
    • Advertise

    • RSS Feed
    • Site Map
  • About
  • Privacy
  • Contact Us
  • Promotional Opportunities @ CdrInfo.com
  • Advertise on out site
  • Submit your News to our site
  • RSS Feed