Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions
This paper describes Tacotron 2, a neural network architecture for speech synthesis directly from text. The system is composed of a recurrent sequence-to-sequence feature prediction network that maps character embeddings to mel-scale spectrograms, followed by a modified WaveNet model acting as a vocoder to synthesize timedomain waveforms from those spectrograms. Our model achieves a mean opinion score (MOS) of $4.53$ comparable to a MOS of $4.58$ for professionally recorded speech. To validate our design choices, we present ablation studies of key components of our system and evaluate the impact of using mel spectrograms as the input to WaveNet instead of linguistic, duration, and $F_0$ features. We further demonstrate that using a compact acoustic intermediate representation enables significant simplification of the WaveNet architecture.
Code (33)
Tasks
Speech SynthesisMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Parallel WaveNet conditioned on VAE latent vectors
Recently the state-of-the-art text-to-speech synthesis systems have shifted to a two-model approach: a sequence-to-sequence model to predict a representation of speech (typically mel-spectrograms), followed by a 'neural …
SentenceSpeech Synthesistext-to-speechText to Speech+1GELP: GAN-Excited Linear Prediction for Speech Synthesis from Mel-spectrogram
Recent advances in neural network -based text-to-speech have reached human level naturalness in synthetic speech. The present sequence-to-sequence models can directly map text to mel-spectrogram acoustic features, which …
Speech Synthesistext-to-speechText to SpeechParametric Resynthesis with neural vocoders
Noise suppression systems generally produce output speech with compromised quality. We propose to utilize the high quality speech generation capability of neural vocoders for noise suppression. We use a neural network to…
ResynthesisHigh-quality Speech Synthesis Using Super-resolution Mel-Spectrogram
In speech synthesis and speech enhancement systems, melspectrograms need to be precise in acoustic representations. However, the generated spectrograms are over-smooth, that could not produce high quality synthesized spe…
Image-to-Image TranslationSpeech EnhancementSpeech SynthesisSuper-Resolution+2Towards Robust FastSpeech 2 by Modelling Residual Multimodality
State-of-the-art non-autoregressive text-to-speech (TTS) models based on FastSpeech 2 can efficiently synthesise high-fidelity and natural speech. For expressive speech datasets however, we observe characteristic audio d…
Decodertext-to-speechText to Speech