Augmented Prompt Selection for Evaluation of Spontaneous Speech Synthesis

no code implementations • LREC 2020 • Eva Szekely, Jens Edlund, Joakim Gustafson

Spontaneous speech is emergent and transient, whereas text read out loud is pre-planned.

Speech Synthesis

Bringing Order to Chaos: A Non-Sequential Approach for Browsing Large Sets of Found Audio Data

no code implementations • LREC 2018 • Per Fallgren, Zofia Malisz, Jens Edlund

Dimensionality Reduction

Hidden Resources ― Strategies to Acquire and Exploit Potential Spoken Language Resources in National Archives

no code implementations • LREC 2016 • Jens Edlund, Joakim Gustafson

In 2014, the Swedish government tasked a Swedish agency, The Swedish Post and Telecom Authority (PTS), with investigating how to best create and populate an infrastructure for spoken language resources (Ref N2014/2840/ITP).

Position

Human pause and resume behaviours for unobtrusive humanlike in-car spoken dialogue systems

no code implementations • WS 2014 • Jens Edlund, Fredrik Edelstam, Joakim Gustafson

Spoken Dialogue Systems

3rd party observer gaze as a continuous measure of dialogue flow

no code implementations • LREC 2012 • Jens Edlund, Alex, Simon ersson, Jonas Beskow, Lisa Gustavsson, Mattias Heldner, Anna Hjalmarsson, Petter Kallionen, Ellen Marklund

We present an attempt at using 3rd party observer gaze to get a measure of how appropriate each segment in a dialogue is for a speaker change.

Action Detection