Abstract: In pursuit of high inference speed, many non-autoregressive neural text-to-speech models have been proposed for parallel speech synthesis recently. A critical challenge of parallel speech generation lies in the learning of text-speech alignment. Existing methods usually require an external aligner for guidance or involve complex training process. In this work, we propose a simple and efficient parallel text-to-speech architecture which jointly learns duration prediction, text-speech alignment and speech generation in a single fully-differentiable model. The alignment is learned implicitly in our architecture. A novel energy-modulated attention mechanism is proposed for alignment guidance which leads to fast and stable convergence of our model. Our model can be easily implemented and trained. Experiments demonstrate that our method can generate speech of high quality with high training efficiency.
| GT-Mel | Tacotron2 | Glow-TTS | EF-TTS | Eden-TTS |
|---|---|---|---|---|
| might have been more alert in the Dallas motorcade if they had retired promptly in Fort Worth. | ||||
| Roupell received the announcement with a cheerful countenance, | ||||
| Yet the public opinion of the whole body seems to have checked dissipation. | ||||
| Caslon's type is clear and neat, and fairly well designed; | ||||
| and paying great attention to the "press work" or actual process of printing, | ||||
| who was presently attacked in the same way as the others, but, but, thanks to the prompt administration of remedies, he recovered. | ||||
| GT-Mel | Tacotron2 | Glow-TTS | EF-TTS | Eden-TTS |
|---|---|---|---|---|
| were induced to cut punches for a series of "old style" letters. | ||||
| otherwise he would have been stripped of his clothes. End quote. | ||||
| The boy declared he saw no one, and accordingly passed through without paying the toll of a penny. | ||||
| Mr. Buxton's friends at once paid the forty shillings, and the boy was released. | ||||
| Here and there a book is printed in France or Germany with some pretension to good taste, | ||||
| were governed by rules which they themselves had framed, and under which subscriptions were levied | ||||
| each patrolman might be given a prepared booklet of instructions explaining what is expected of him. The Secret Service has expressed concern | ||||
| Tacotron2 | Glow-TTS | Eden-TTS | EF-TTS | |
|---|---|---|---|---|
| Do not impose on others what you yourself do not desire. Don't do unto others what you don't want others do unto you. | ||||
| Is not he a superior man, who does not feel indignant when men are blind to his merits! | ||||
| The world is a fine place and worth the fighting for and I hate very much to leave it. | ||||
| Happiness in intelligent people is the rarest thing I know. | ||||
| distance makes the heart grow fonder. | ||||
But in the interval very comprehensive and, I think it must be admitted, salutary changes were successively introduced into the management of prisons.
| x 0.6 | x 0.8 | x 1.00 | x 1.2 | x 1.6 | x 2.0 |
|---|---|---|---|---|---|
to be or not to be this is a question.
| x 0.6 | x 0.8 | x 1.00 | x 1.2 | x 1.6 | x 2.0 |
|---|---|---|---|---|---|
For a while the preacher addresses himself to the congregation at large, who listen attentively
| x 0.6 | x 0.8 | x 1.00 | x 1.2 | x 1.6 | x 2.0 |
|---|---|---|---|---|---|
| Tacotron2 | Glow-TTS | Eden-TTS | EF-TTS | |
|---|---|---|---|---|
| Sorry," he grunted, as the tiny old man stumbled and almost fell. It was a few seconds before Mr. Dursley realized that the man was wearing a violet cloak. He didn't seem at all upset at being almost knocked to the ground. On the contrary, his face split into a wide smile and he said in a squeaky voice that made passersby stare, "Don't be sorry, my dear sir, for nothing could upset me today! Rejoice, for You-Know-Who has gone at last! Even Muggles like yourself should be celebrating, this happy, happy day! | ||||
| While technology continues to improve, there are still many things that human beings can do much more effectively than computers, such as moderating content, performing data deduplication, or research. Traditionally, tasks like this have been accomplished by hiring a large temporary workforce, which is time consuming, expensive and difficult to scale, or have gone undone. Crowdsourcing is a good way to break down a manual, time-consuming project into smaller, more manageable tasks to be completed by distributed workers over the Internet (also known as ‘microtasks’). | ||||
| Previous efforts to achieve global peace have all been full of good intentions, but they resulted in too many declarations and not enough action. This is a historic moment, and if we do not seize it, maybe we do not deserve to survive. As is the case when launching a rocket to meet the International Space Station in orbit, there is a very small window of opportunity to make world peace happen. Protecting the existence of all species, sustaining life on Earth, exploring outer space, tackling disease and mortality, solving the pollution problem, coexisting with the environment, electing more women to leadership positions and creating real freedom that includes true private property: world peace is a prerequisite for all of these objectives. | ||||