亚马逊人工智能研究团队宣布成功开发了一个史上最大的文本转语音模型，名为“可扩展流式文本转语音模型”（BASE TTS）。该模型拥有9.8亿个参数，并使用了10万小时的录音进行训练，其中大部分为英语语音。
这一突破性的技术进展展示了亚马逊在人工智能领域的强大实力。据研究团队在arXiv预印本服务器上发表的论文介绍，BASE TTS模型在参数数量和训练数据集大小上都创下了历史纪录。这使得模型能够更准确地模拟人类语音，提高语音合成的自然度和流畅度。
BASE TTS模型的开发和训练过程也标志着亚马逊在文本转语音技术上的重要突破。该模型能够处理更复杂的语音合成任务，为语音助手、自动电话系统、语音合成等领域提供了更高效、更自然的解决方案。
With the release of the largest-ever text-to-speech model, Amazon AI research team has showcased its strong capabilities in the field of artificial intelligence. As described in a paper published on the arXiv preprint server, the new model, named BASE TTS, sets records in terms of parameter numbers and training dataset size. This groundbreaking technological advancement enables the model to simulate human speech more accurately, enhancing the naturalness and fluency of speech synthesis.
The development and training process of the BASE TTS model also marks a significant breakthrough for Amazon in text-to-speech technology. The model is capable of handling more complex speech synthesis tasks, providing more efficient and natural solutions for applications such as voice assistants, automated telephone systems, and speech synthesis.
【来源】https://www.ithome.com/0/750/680.htm
Views: 1