|
The listening talker| old_uid | 11310 |
|---|
| title | The listening talker |
|---|
| start_date | 2012/04/26 |
|---|
| schedule | 13h30 |
|---|
| online | no |
|---|
| location_info | Ampère, salle B314 |
|---|
| summary | Speech is efficient and robust, and remains the method of choice for human
communication. Consequently, speech output is used increasingly to deliver
information in automated systems such as talking GPS and live-but-remote
forms such as public address systems. However, these systems are essentially
one-way, output-oriented technologies that lack an essential ingredient of
human interaction: communication. When people speak, they also listen. When
machines speak, they do not listen. As a result, there is no guarantee that the
intended message is intelligible, appropriate or well-timed, key considerations in
safety-critical environments. Starting with a review of recent behavioural
findings on speech modifications in the face of a range of maskers, including
competing speakers, this talk will examine how knowledge about human
talkers' response to noise can be applied to improve the intelligibility of
synthetic, recorded or live speech under constraints on overall level and
duration. I'll conclude with results from a recent large-scale listener evaluation
of the intelligibility of modified natural and synthetic speech in stationary and
non-stationary maskers. |
|---|
| responsibles | Loevenbruck, Welby |
|---|
| |
|