21 citations · 41 across the 8 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
eess.AS2021★ 1 cited
Generalizing RNN-Transducer to Out-Domain Audio via Sparse Self-Attention Layers
Juntae Kim, Jeehye Lee
Recurrent neural network transducer (RNN-T) is an end-to-end speech recognition framework converting input acoustic frames into a character sequence. The state-of-the-art encoder n…
eess.AS2021★ 4 cited
UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation
Won Jang, Dan Lim, Jaesam Yoon +2
Most neural vocoders employ band-limited mel-spectrograms to generate waveforms. If full-band spectral features are used as the input, the vocoder can be provided with as much acou…