Speech dereverberation using long short-term memory.
Masato MimuraShinsuke SakaiTatsuya KawaharaPublished in: INTERSPEECH (2015)
Keyphrases
- recurrent neural networks
- long short term memory
- speech recognition
- text to speech
- speech signal
- recognition engine
- endpoint detection
- automatic speech recognition
- spoken language
- databases
- human computer interaction
- hidden markov models
- dialogue system
- language acquisition
- speaker recognition
- information systems
- speech synthesis
- feed forward
- audio visual
- artificial neural networks
- speaker identification
- speech processing
- social networks
- genetic algorithm
- text to speech synthesis
- neural network