Speech Research at Google to Enable Universal Speech Interfaces

Cinefluorographic Speech Research

Journal of Speech and Hearing Research ◽

10.1044/jshr.0402.171 ◽

1961 ◽

Vol 4 (2) ◽

pp. 171-171

Author(s):

Ralph L. Shelton

Keyword(s):

Speech Research

Download Full-text

Cinefluorographic Techniques in Speech Research

Journal of Speech and Hearing Research ◽

10.1044/jshr.0303.227 ◽

1960 ◽

Vol 3 (3) ◽

pp. 227-241 ◽

Cited By ~ 36

Author(s):

Kenneth L. Moll

Keyword(s):

Speech Research

Download Full-text

DOING L2 SPEECH RESEARCH ONLINE: WHY AND HOW TO COLLECT ONLINE RATINGS DATA

Studies in Second Language Acquisition ◽

10.1017/s0272263121000292 ◽

2021 ◽

pp. 1-24

Author(s):

Charles L. Nagle ◽

Ivana Rehman

Keyword(s):

Intraclass Correlation ◽

Correlation Coefficients ◽

Control Measures ◽

Mixed Effects Models ◽

Amazon Mechanical Turk ◽

Intraclass Correlation Coefficients ◽

Online Ratings ◽

Speech Research ◽

Future Work ◽

Local Laboratory

Abstract Listener-based ratings have become a prominent means of defining second language (L2) users’ global speaking ability. In most cases, local listeners are recruited to evaluate speech samples in person. However, in many teaching and research contexts, recruiting local listeners may not be possible or advisable. The goal of this study was to hone a reliable method of recruiting listeners to evaluate L2 speech samples online through Amazon Mechanical Turk (AMT) using a blocked rating design. Three groups of listeners were recruited: local laboratory raters and two AMT groups, one inclusive of the dialects to which L2 speakers had been exposed and another inclusive of a variety of dialects. Reliability was assessed using intraclass correlation coefficients, Rasch models, and mixed-effects models. Results indicate that online ratings can be highly reliable as long as appropriate quality control measures are adopted. The method and results can guide future work with online samples.

Download Full-text

The State of Speech in HCI: Trends, Themes and Challenges

Interacting with Computers ◽

10.1093/iwc/iwz016 ◽

2019 ◽

Vol 31 (4) ◽

pp. 349-371 ◽

Cited By ~ 18

Author(s):

Leigh Clark ◽

Philip Doyle ◽

Diego Garaialde ◽

Emer Gilmartin ◽

Stephan Schlögl ◽

...

Keyword(s):

Speech Production ◽

Thematic Analysis ◽

Design Work ◽

Wizard Of Oz ◽

Speech Interfaces ◽

Interface Interaction ◽

Multiple User ◽

Speech Interface ◽

User Attitudes ◽

In The Wild

AbstractSpeech interfaces are growing in popularity. Through a review of 99 research papers this work maps the trends, themes, findings and methods of empirical research on speech interfaces in the field of human–computer interaction (HCI). We find that studies are usability/theory-focused or explore wider system experiences, evaluating Wizard of Oz, prototypes or developed systems. Measuring task and interaction was common, as was using self-report questionnaires to measure concepts like usability and user attitudes. A thematic analysis of the research found that speech HCI work focuses on nine key topics: system speech production, design insight, modality comparison, experiences with interactive voice response systems, assistive technology and accessibility, user speech production, using speech technology for development, peoples’ experiences with intelligent personal assistants and how user memory affects speech interface interaction. From these insights we identify gaps and challenges in speech research, notably taking into account technological advancements, the need to develop theories of speech interface interaction, grow critical mass in this domain, increase design work and expand research from single to multiple user interaction contexts so as to reflect current use contexts. We also highlight the need to improve measure reliability, validity and consistency, in the wild deployment and reduce barriers to building fully functional speech interfaces for research.RESEARCH HIGHLIGHTSMost papers focused on usability/theory-based or wider system experience research with a focus on Wizard of Oz and developed systems Questionnaires on usability and user attitudes often used but few were reliable or validated Thematic analysis showed nine primary research topics Challenges identified in theoretical approaches and design guidelines, engaging with technological advances, multiple user and in the wild contexts, critical research mass and barriers to building speech interfaces

Download Full-text

Some Recent Developments in the Use of Electromyography in Speech Research

Journal of Speech and Hearing Research ◽

10.1044/jshr.1402.241 ◽

1971 ◽

Vol 14 (2) ◽

pp. 241-246 ◽

Cited By ~ 4

Author(s):

Thomas Gay ◽

Katherine S. Harris

Keyword(s):

Data Reduction ◽

Recent Developments ◽

Speech Research ◽

Instrumental Methods ◽

Electrode Systems ◽

Averaging Techniques

This paper describes current instrumental methods of obtaining and processing electromyographic data for the study of speech. Methods described include electrode systems, data reduction operations; and computer averaging techniques. The particular problems associated with each method are discussed.

Download Full-text