A Comparative Study on Transformer vs RNN in Speech Applications.
Shigeki KaritaNanxin ChenTomoki HayashiTakaaki HoriHirofumi InagumaZiyan JiangMasao SomekiNelson Enrique Yalta SoplinRyuichi YamamotoXiaofei WangShinji WatanabeTakenori YoshimuraWangyou ZhangPublished in: CoRR (2019)
Keyphrases
- recurrent neural networks
- speech recognition
- nearest neighbor
- fault diagnosis
- fuzzy logic
- speech signal
- spoken language
- power system
- comparative study
- audio visual
- automatic speech recognition
- speech synthesis
- vocal tract
- power transformers
- recognition engine
- distribution network
- endpoint detection
- neural network
- audio stream
- text to speech synthesis
- hearing impaired
- speech processing
- speaker verification
- speaker identification
- emotion recognition
- pattern recognition