rospeex

A Cloud-based speech communication toolkit for ROS
2013/12/13

Komei Sugiura
National Institute of Information an...
ROS (Robot Operating System)
• ROS: middleware for robots
– Version 1.0 released in 2010
– Global de facto standard
– From...
Speech communication toolkit for ROS

rospeex

• ROS compatible
• Speech recognition using VoiceTra engine
• Other functio...
Position in Cloud Robotics
• Cloud robotics [James Kuffner@Google, 2011]
– Manipulation using Google Goggles [Kehoe+ 2013]...
Quadrilingual communication using rospeex

5
rospeex provides speech recognition/synthesis,
user constructs dialogue processing
Input from other modules
(Sensors, reco...
Non-monologue speech synthesis for robots
• Reading-style robot voice
– Monotonous, unnatural and unfriendly
– Hard to rea...
Demo
http://komeisugiura.jp/software/nm_tts.html

8
Using speech recognition/synthesis without ROS
• Send JSON file to the server
– Recognition http://rospeex.ucri.jgn-x.jp/n...
Upcoming SlideShare
Loading in …5
×

rospeex: a cloud-based speech communication toolkit for ROS

1,207 views

Published on

Published in: Technology, Education
0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total views
1,207
On SlideShare
0
From Embeds
0
Number of Embeds
184
Actions
Shares
0
Downloads
6
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide

rospeex: a cloud-based speech communication toolkit for ROS

  1. 1. rospeex A Cloud-based speech communication toolkit for ROS 2013/12/13 Komei Sugiura National Institute of Information and Communication Technology, Japan komei.sugiura@nict.go.jp
  2. 2. ROS (Robot Operating System) • ROS: middleware for robots – Version 1.0 released in 2010 – Global de facto standard – From driver and package management to learning and visualization 2
  3. 3. Speech communication toolkit for ROS rospeex • ROS compatible • Speech recognition using VoiceTra engine • Other functionalities – Noise reduction, non-monologues speech synthesis Conventional packages rospeex Speech recognition/ Sphinx, festival, Julius VoiceTra engine synthesis (or commercial tools) (or third-party engines) Engine Stand alone Cloud-based Language Single language ja, en, zh, ko 3
  4. 4. Position in Cloud Robotics • Cloud robotics [James Kuffner@Google, 2011] – Manipulation using Google Goggles [Kehoe+ 2013] – Knowledge sharing based on RoboEarth [Tenorth+ 2012] – Speech communication for robots rospeex Cloud-based Incompatible Commercial systems (Nuance, ToSpeak, AmiVoice Cloud, ..) rospeex Many OpenHRI, HARK, PocketSphinx, Festival Stand-alone Robot middleware compatible
  5. 5. Quadrilingual communication using rospeex 5
  6. 6. rospeex provides speech recognition/synthesis, user constructs dialogue processing Input from other modules (Sensors, recognized obj, etc) Speech input Noise reduction VAD Task manager Output to other modules (Actuators, learning, etc) Speech module Speech recognition Dialogue processing Speech synthesis Speech output Speech recognition & synthesis servers Provided by rospeex Provided by the user Provided by third parties Speech recognition & synthesis servers
  7. 7. Non-monologue speech synthesis for robots • Reading-style robot voice – Monotonous, unnatural and unfriendly – Hard to realize that the robot is asking a question XIMERA 3 (Text reading) Voice talent • Conventional text-to-speech (TTS) systems are not optimized for communication 7
  8. 8. Demo http://komeisugiura.jp/software/nm_tts.html 8
  9. 9. Using speech recognition/synthesis without ROS • Send JSON file to the server – Recognition http://rospeex.ucri.jgn-x.jp/nauth_json/jsServices/VoiceTraSS – Synthesis http://rospeex.ucri.jgn-x.jp/nauth_json/jsServices/VoiceTraSR • Sample codes (JavaScript, Python, C++) are available Non-monologue speech synthesis { "method":"recognize", "params":[ "ja", {“audio”:“base64-encoded wav", "audioType":"audio/x-wav", "voiceType":"*" }]} Recognition Search { “method” : “speak”, "params" : [ "ja", "こんにちは", "*", "audio/x-wav" ]} Synthesis

×