Bridge-net

2000년 도입 · 논문 7편에서 사용

Bridge-net is an audio model block used in the ClariNet text-to-speech architecture. Bridge-net maps frame-level hidden representation to sample-level through several convolution blocks and transposed convolution layers interleaved with softsign non-linearities.

출처: ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech

소개 논문: ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech