Skip to main content Accessibility help

We use cookies to distinguish you from other users and to provide you with a better experience on our websites. Close this message to accept cookies or find out how to manage your cookie settings.

Close cookie message
×
  1. Home
  2. Search

Refine search

Refine search

Access:
Content type:
Publication date:
Apply   From and To filters
Subject: Show more
Journals Show more
Publishers: Show more
Societies Show more
Series: Show more
Collections: Show more

Actions for selected content:

Select all | Deselect all
  • View selected items
  • Export citations
  • Download PDF (zip)
  • Save to Kindle
  • Save to Dropbox
  • Save to Google Drive

Save Search

You can save your searches here and later view and run them again in "My saved searches".

Please provide a title, maximum of 40 characters.
Cancel
×

2 results

  • 15 - Beyond Functional Speech Synthesis

  • from Section III - Measuring Speech
  • Edited by Rachael-Anne Knight, City, University of London, Jane Setter, University of Reading
  • Book:
    The Cambridge Handbook of Phonetics
    Published online:
    11 November 2021
    Print publication:
    02 December 2021, pp 387-404

  • Summary

    As synthetic voices enter the mass market, there is an increasing need for voice personalisation, that is, a voice for the text-to-speech system that not only conveys information but also exudes a persona much like the human voice. We begin this chapter with a historical overview of the field starting with model-based approaches, to concatenative systems and finally to contemporary implementations of parametric synthesis. We then examine how the confluence of increased computational speed at reduced costs, the availability of large data sets, and advances in machine learning and artificial intelligence enable a whole new approach to speech synthesis, including the ability to create high-quality personalised voices. We then examine the role of crowdsourcing in developing a scalable method for voice customisation and adaptation. We discuss the benefits and challenges of acquiring recordings of novice voice talent of all ages from around the world and using these recordings for voice building. We conclude by discussing the impact of personalised voices and implications for future work.

  • Recast type, repair, and acquisition in AAC mediated interaction

  • Gloria SOTO, Michael T. CLARKE, Keith NELSON, Renee STAROWICZ, Gat SAVALDI-HARUSSI
  • Journal:
    Journal of Child Language / Volume 47 / Issue 1 / January 2020
    Published online by Cambridge University Press:
    16 September 2019, pp. 250-264

  • The present study investigated the effects of different types of recasts and prompts on the rate of repair and spontaneous use of novel vocabulary by eight children with severe motor speech disabilities who used speech-generating technologies to communicate. Data came from 60 transcripts of clinical sessions that were part of a conversation-based intervention designed to teach them pronouns, verbs, and verb inflections. The results showed that, when presented alone, interrogative choice and declarative recasts led to the highest rates of child repair. The results also showed that when children were presented with recasts and prompts to repair, the rate of repair increased. Spontaneous use of linguistic targets was significantly and positively related to conversational sequences where the adult recast was followed by child repair. These findings suggest that using different recast types and prompts to repair may be beneficial for spontaneous use of linguistic targets in this population.