Robust speech interface based on audio and video information fusion for humanoid HRP-2.
Isao HaraFutoshi AsanoHideki AsohJun OgataNaoyuki IchimuraYoshihiro KawaiFumio KanehiroHirohisa HirukawaKiyoshi YamamotoPublished in: IROS (2004)
Keyphrases
- information fusion
- emotion recognition
- audio stream
- audio video
- humanoid robot
- data fusion
- broadcast news
- multimedia
- digital audio
- audio signals
- audio visual
- audio features
- fusion algorithm
- soft computing
- content based video retrieval
- visual data
- multi source
- fusion method
- video sequences
- speaker identification
- video streams
- audio files
- multi modal
- information gathering
- fusion model
- speech recognition
- video data
- real time
- media streams
- data mining
- text to speech
- audio signal
- video content
- decision level
- visual information
- pattern recognition
- machine learning
- multi sensor information fusion