Speech Recognition in Mobile Devices

Technologies, Applications, and Markets for Voice Recognition

Research Report

In the past few years, mobile automatic speech recognition (ASR) has made meaningful gains in both recognition accuracy and the complexity of applications that can be delivered on a mobile device. ABI Research believes the recent improvements in mobile ASR have led to a greatly improved end user experience, which in turn drives increased usage of speech capabilities. Following the improved user experiences, mobile speech recognition is given the opportunity to ‘make good’ on the promise of delivering a useful, reliable, hands free interaction methodology that has been promised to users since the beginning of modern speech recognition research.

This study traces the evolution of the underlying technologies that are driving mobile speech recognition applications and services. The report also examines the current and future addressable markets for mobile speech recognition with regard to embedded licensing opportunities and emerging network-based speech recognition services opportunities.

Table of Contents

  • Table 2-1, Application Downloads by Distribution Channel, World Market, Forecast: 2009 to 2015
  • Table 2-2, Available Application in App Stores, Paid versus Free, World Market, Forecast: 2009 to 2015
  • Table 5-1, ASR Embedded Smartphone Shipments by OS, World Market Forecast: 2009 to 2015. Table 5-1, ASR Embedded Smartphone Shipments by OS, World Market, Forecast: 2009 to 2015
  • Table 5-2, ASR Embedded PND and In-Dash Automotive Shipments by Device Type, World Market Forecast: 2009 to 2015. Table 5-2, ASR Embedded PND and In-Dash Automotive Shipments by Device Type, World Market, Forecast: 2009 to 2015
  • Table 5-3, ASR Embedded CE Shipments by Device Type, World Market Forecast: 2009 to 2015. Table 5-3, ASR Embedded CE Shipments by Device Type, World Market, Forecast: 2009 to 2015
  • Table 5-4, ASR Embedded Licensing Revenues by Device Segment, World Market, Forecast: 2009 to 2015
  • Table 5-5, Mobile ASR Service Subscribers by Region, World Market Forecast: 2009 to 2015. Table 5-5, Mobile ASR Service Subscribers by Region, World Market, Forecast: 2009 to 2015
  • Table 5-6, Mobile ASR Service Subscribers by Region, World Market Forecast: 2009 to 2015. Table 5-6, Mobile ASR Service Subscribers by Region, World Market, Forecast: 2009 to 2015
  • Chart 1-1, Mobile ASR Revenues, Embedded Licensing and Speech Services, World Market, Forecast: 2009 to 2015
  • Chart 1-2, Mobile ASR Embedded Licensing Revenues by Device Segment, World Market, Forecast: 2009 to 2015
  • 1. Executive Summary
    • 1.1. Mobile Speech Recognition
      • 1.1.1. Embedded Speech Recognition
      • 1.1.2. Network-Based Speech Recognition
    • 1.2. Market Overview
  • 2. Market Issues
    • 2.1. Market Overview
      • 2.1.1. Speech Recognition Engines
      • 2.1.2. Speech Recognition Platforms
      • 2.1.3. Revenue Opportunities for Speech-Enabled Applications
    • 2.2. Drivers of Mobile Speech Recognition
      • 2.2.1. Service and Content Discovery
      • 2.2.2. Voice Control as a Utility
      • 2.2.3. Improved Recognition Accuracy
      • 2.2.4. Increased Processing Power in Handsets and Mobile Devices
      • 2.2.5. Increased Smartphone and 3G Penetration
      • 2.2.6. Automotive ASR
      • 2.2.7. Telecommunications Act, Section 255 - Accessibility
      • 2.2.8. Speech as a Service
    • 2.3. Mobile Speech Recognition Barriers
      • 2.3.1. Consumer Awareness and Perception
      • 2.3.2. Real World Mobile Usage
      • 2.3.3. Recognition Engine Development and Talent Acquisition
    • 2.4. Critical Concerns
      • 2.4.1. The Oligarchy of Embedded Mobile Speech Applications
      • 2.4.2. Implications of Mobile Application Storefront Choice
  • 3. Technology Issues
    • 3.1. Mobile Speech Recognition Defined
    • 3.2. Historical Development of Speech Recognition
    • 3.3. Traditional Speech Recognition Concepts
      • 3.3.1. Embedded Speech Recognition
      • 3.3.2. Network-Based Speech Recognition
      • 3.3.3. Hybrid or Distributed Speech Recognition
      • 3.3.4. Speaker Dependency
      • 3.3.5. Hidden Markov Model
      • 3.3.6. Context-Free or Natural Language Input
      • 3.3.7. Ambient Noise and the Mobile Environment
      • 3.3.8. Multimodal Interaction
      • 3.3.9. Speech Synthesis or Text-to-Speech
    • 3.4. Programming Standards for Speech Recognition
      • 3.4.1. VoiceXML
      • 3.4.2. Call Control XML
      • 3.4.3. Speech Recognition Grammar Specifications
      • 3.4.4. Semantic Interpretation for Speech Recognition
      • 3.4.5. Speech Synthesis Markup Language
      • 3.4.6. Extensible MultiModal Annotation
    • 3.5. Processing Requirements for Speech Recognition
  • 4. Key Industry Players
    • 4.1. Loquendo
    • 4.2. Promptu
    • 4.3. IBM
    • 4.4. Vlingo (AT&T;)
    • 4.5. Google
    • 4.6. Tellme (Microsoft)
    • 4.7. Yap
    • 4.8. Nuance
    • 4.9. Sensory Inc
    • 4.10. SVOX
  • 5. Market Forecasts
    • 5.1. Embedded Speech Recognition in Smartphones
    • 5.2. Embedded Speech Recognition in PNDs
    • 5.3. Embedded Speech Recognition in Mobile CE
    • 5.4. Embedded Speech Recognition Licensing Revenues
    • 5.5. Speech Recognition Service Subscriptions
    • 5.6. Speech Recognition Service Revenues
  • 6. Company Directory
  • 7. Acronyms

Tables

Log in to view the structure of the tables below.

  1. Application Downloads by Distribution Channel, World Market, Forecast: 2009 to 2015
  2. Available Application in App Stores, Paid versus Free, World Market, Forecast: 2009 to 2015
  3. ASR Embedded Smartphone Shipments by OS, World Market Forecast: 2009 to 2015
  4. ASR Embedded PND and In-Dash Automotive Shipments by Device Type, World Market Forecast: 2009 to 2015
  5. ASR Embedded CE Shipments by Device Type, World Market Forecast: 2009 to 2015
  6. ASR Embedded Licensing Revenues by Device Segment, World Market Forecast: 2009 to 2015
  7. Mobile ASR Service Subscribers by Region, World Market Forecast: 2009 to 2015
  8. Mobile ASR Service Revenues by Region, World Market Forecast: 2009 to 2015

Figures

  1. NIST Speech Recognition Benchmark Results
  2. Recognition Complexity Compared to Speaking Style and Vocabulary Size