All of the audio samples use MelGAN as vocoder. When a man looks for something beyond his reach, his friends say he is looking for the pot of gold at the end of the rainbow. Some have accepted it as a miracle without physical explanation. t…
* Equal contribution. ^ Corresponding author. Automatic song writing aims to compose a song (lyric and/or melody) by machine, which is an interesting topic in both academia and industry. In automatic song writing, lyric-to-melody generation…
Speech conveys more information than text, as the same word can be uttered in various voices to convey diverse information. Compared to traditional text-to-speech (TTS) methods relying on speech prompts (reference speech) for voice variabil…
Text to speech (TTS) has been broadly used to synthesize natural and intelligible speech in different scenarios. Deploying TTS in various end devices such as mobile phones or embedded devices requires extremely small memory usage and infere…
ArXiv: arXiv:2006.07926 (Accepted by AAAI2021) Existing speech to speech translation systems heavily rely on the text of target language: they usually translate source language either to target text and then synthesize target speech from te…
VCTK speaker : Six spoons of fresh snow peas, five thick slabs of blue cheese, and maybe a snack for her brother Bob. LibriTTS speaker : The hectic flushed into her thin cheeks, but her voice sounded calm as before. VCTK speaker : Six spoon…
P.S. 1) $\textit{GT}$, the ground-truth audio; 2) $\textit{GT (Linear+GL)}$, where we synthesize voices based on the ground-truth linear-spectrograms using Griffin-Lim; 3) $\textit{DeepSinger}$, where the audio is generated by DeepSinger. A…
Speech synthesis (text to speech, TTS) and recognition (automatic speech recognition, ASR) are important speech tasks, and require a large amount of text and speech pairs for model training. However, there are more than 6,000 languages in t…
Neural architecture search (NAS) relies on a good controller to generate better architectures or predict the accuracy of given architectures. However, training the controller requires both abundant and high-quality pairs of architectures an…
Neural network based end-to-end text to speech (TTS) has significantly improved the quality of synthesized speech. Prominent methods (e.g., Tacotron 2) usually first generate mel-spectrogram from text, and then synthesize speech from mel-sp…
Non-autoregressive text to speech (TTS) models such as FastSpeech~\citep{ren2019fastspeech} can synthesize speech significantly faster than previous autoregressive models with comparable quality. The training of FastSpeech model relies on a…
Text to speech (TTS) and automatic speech recognition (ASR) are two dual tasks in speech processing and both achieve impressive performance thanks to the recent advance in deep learning and large amount of aligned speech and text data. Howe…