We introduce a text-to-speech (TTS) model called BASE TTS, which stands for $\textbf{B}$ig $\textbf{A}$daptive $\textbf{S}$treamable TTS with $\textbf{E}$mergent abilities. BASE TTS is the largest TTS model to-date, trained on 100K hours of public domain speech data, achieving a new state-of-the-art in speech naturalness. It deploys a 1-billion-parameter autoregressive Transformer that converts raw texts into discrete codes ("speechcodes") followed by a convolution-based decoder which converts these speechcodes into waveforms in an incremental, streamable manner. Further, our speechcodes are built using a novel speech tokenization technique that features speaker ID disentanglement and compression with byte-pair encoding. Echoing the widely-reported "emergent abilities" of large language models when trained on increasing volume of data, we show that BASE TTS variants built with 10K+ hours and 500M+ parameters begin to demonstrate natural prosody on textually complex sentences. We design and share a specialized dataset to measure these emergent abilities for text-to-speech. We showcase state-of-the-art naturalness of BASE TTS by evaluating against baselines that include publicly available large-scale text-to-speech systems: YourTTS, Bark and TortoiseTTS. Audio samples generated by the model can be heard at https://amazon-ltts-paper.com/.

翻译：我们提出一种名为BASE TTS的文本转语音（TTS）模型，其全称为$\textbf{B}$ig $\textbf{A}$daptive $\textbf{S}$treamable TTS with $\textbf{E}$mergent abilities（具备涌现能力的大规模自适应可流式TTS）。BASE TTS是迄今最大的TTS模型，基于10万小时公共领域语音数据训练，在语音自然度方面达到了新标杆。该模型采用包含10亿参数的自回归Transformer将原始文本转换为离散编码（"语音编码"），随后通过基于卷积的解码器将这些语音编码以增量式、可流式的方式转换为波形。此外，我们通过一种新型语音分词技术构建语音编码，该技术采用说话人身份解耦与字节对编码压缩。与广泛报道的大语言模型在数据量递增时涌现能力相呼应，我们证明基于1万小时以上数据和5亿以上参数构建的BASE TTS变体，已能在文本复杂句子中展现自然韵律。我们设计并共享了专门数据集以衡量文本转语音领域的这些涌现能力。通过与包括公开可用的YourTTS、Bark和TortoiseTTS等大规模文本转语音系统在内的基线进行对比评估，我们展示了BASE TTS在自然度方面达到的领先水平。模型生成的音频样本可在https://amazon-ltts-paper.com/收听。