语音相关论文总结

1. 声码器

1. 20201023 HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis https://arxiv.org/abs/2010.05646
2. 20200512 FeatherWave: An efficient high-fidelity neural vocoder with multi-band linear prediction
3. BLSTM
4. Transformer-TTS
5. CNN blocks

2. 音素对齐

1. 20170820 Montreal Forced Aligner: trainable text-speech alignment using Kaldi https://www.isca-speech.org/archive/Interspeech_2017/pdfs/1386.PDF

3. TTS

1. 20180216 Tacotron2：NATURAL TTS SYNTHESIS BY CONDITIONING WAVENET ON MEL SPECTROGRAM
   PREDICTIONS https://arxiv.org/pdf/1712.05884.pdf
2. 20180222 Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning https://arxiv.org/pdf/1710.07654.pdf
3. 20180919 Transformer-TTS: Neural Speech Synthesis with Transformer Network https://arxiv.org/abs/1809.08895v1
4. 20190512 Waveglow: A Flow-based Generative Network for Speech Synthesis https://ieeexplore.ieee.org/document/8683143/
5. 20201023 Glow-TTS：A Generative Flow for Text-to-Speech via Monotonic Alignment Search https://arxiv.org/abs/2005.11129
6. 20210304 FastSpeech 2: Fast and High-Quality End-to-End Text to Speech https://arxiv.org/abs/2006.04558
7. 202103 BVAE-TTS：BIDIRECTIONAL VARIATIONAL INFERENCE FOR
   NON-AUTOREGRESSIVE TEXT-TO-SPEECH https://openreview.net/pdf?id=o3iritJHLfO