BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Asia/Kolkata
BEGIN:STANDARD
DTSTART:19451014T230000
TZOFFSETFROM:+0630
TZOFFSETTO:+0530
TZNAME:IST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20150801T155709Z
UID:D03E5D81-384B-11E5-A923-0050568D2FB3
DTSTART;TZID=Asia/Kolkata:20150809T110000
DTEND;TZID=Asia/Kolkata:20150809T120000
DESCRIPTION:A lot of progress has been made in the field of speech synthesi
 s in the last few years. Today's synthetic voices sound natural and are qu
 ite intelligible. A lot of this progress can be attributed to "resource de
 velopment" in languages. Large databases of speech\, linguistic analysis t
 ools\, pronunciation dictionaries\, text processing rules\, etc. can help 
 make synthetic speech significantly better. However\, this privileged "res
 ource development" is only enjoyed by a few languages of the world. Text t
 o speech (TTS) has become a common utility today. We now hear synthetic vo
 ices at airports\, railway stations\, in our GPS navigation devices\, and 
 even in toys. This phenomenon has led to an increasing demand for deployin
 g TTS in localized languages. Most of these languages belong to the "low-r
 esource" category. Although linguistic resource development work is happen
 ing at a fast pace for Indian languages\, for many tasks\, they still fall
  in the low resource category. In this talk\, we will take a look at some 
 challenges in building TTS systems for low resource languages. We will dis
 cuss in detail the challenge of inserting pauses between words (phrasing) 
 in synthetic speech and look at novel data driven techniques that also wor
 k in low resource scenarios.\n\nCo-sponsored by: IEEE-RAS\n\nSpeaker(s): A
 LOK PARLIKAR\, \n\nBldg: Auditorium\, IIIT A\, Jhalwa Campus\, Deoghat\, A
 llahabad\, Uttar Pradesh\, India\, 211012
LOCATION:Bldg: Auditorium\, IIIT A\, Jhalwa Campus\, Deoghat\, Allahabad\, 
 Uttar Pradesh\, India\, 211012
ORGANIZER:g.c.nandi@ieee.org
SEQUENCE:3
SUMMARY:On Generating synthetic voices for Low-Resource Languages
URL;VALUE=URI:https://events.vtools.ieee.org/m/35452
X-ALT-DESC:Description: <br /><p>A lot of progress has been made in the fie
 ld of speech synthesis in the last few years. Today's synthetic voices sou
 nd natural and are quite intelligible. A lot of this progress can be attri
 buted to "resource development" in languages. Large databases of speech\, 
 linguistic analysis tools\, pronunciation dictionaries\, text processing r
 ules\, etc. can help make synthetic speech significantly better. However\,
  this privileged "resource development" is only enjoyed by a few languages
  of the world. Text to speech (TTS) has become a common utility today. We 
 now hear synthetic voices at airports\, railway stations\, in our GPS navi
 gation devices\, and even in toys. This phenomenon has led to an increasin
 g demand for deploying TTS in localized languages. Most of these languages
  belong to the "low-resource" category. Although linguistic resource devel
 opment work is happening at a fast pace for Indian languages\, for many ta
 sks\, they still fall in the low resource category. In this talk\, we will
  take a look at some challenges in building TTS systems for low resource l
 anguages. We will discuss in detail the challenge of inserting pauses betw
 een words (phrasing) in synthetic speech and look at novel data driven tec
 hniques that also work in low resource scenarios.</p>
END:VEVENT
END:VCALENDAR