A deep recurrent approach for acoustic-to-articulatory inversion.
Peng LiuQuanjie YuZhiyong WuShiyin KangHelen M. MengLianhong CaiPublished in: ICASSP (2015)
Keyphrases
- acoustic features
- speech recognition
- underwater acoustic
- recurrent neural networks
- speech recognition systems
- speaker verification
- image reconstruction
- feed forward
- vocal tract
- automatic speech recognition
- speech signal
- music information retrieval
- visual features
- bird species
- data sets
- source localization
- formant frequencies
- recurrent networks
- spiking neural networks
- pattern recognition
- information systems
- speech sounds
- search engine