Text-to-speech (TTS) systems are an important component in voice-based
e-commerce applications. These applications include end-to-end voice assistant
and customer experience (CX) voice bot. Code-mixed TTS is also relevant in
these applications since the product names are commonly described in English
while the surrounding text is in a regional language. In this work, we describe
our approaches for production quality code-mixed Hindi-English TTS systems
built for e-commerce applications. We propose a data-oriented approach by
utilizing monolingual data sets in individual languages. We leverage a
transliteration model to convert the Roman text into a common Devanagari script
and then combine both datasets for training. We show that such single script
bi-lingual training without any code-mixing works well for pure code-mixed test
sets. We further present an exhaustive evaluation of single-speaker adaptation
and multi-speaker training with Tacotron2 + Waveglow setup to show that the
former approach works better. These approaches are also coupled with transfer
learning and decoder-only fine-tuning to improve performance. We compare these
approaches with the Google TTS and report a positive CMOS score of 0.02 with
the proposed transfer learning approach. We also perform low-resource voice
adaptation experiments to show that a new voice can be onboarded with just 3
hrs of data. This highlights the importance of our pre-trained models in
resource-constrained settings. This subjective evaluation is performed on a
large number of out-of-domain pure code-mixed sentences to demonstrate the high
quality of the systems.

我们提出了适用于电子商务应用的生产级代码混合印地语 - 英语 TTS 系统的方法。我们采用了一种以数据为导向的方法，通过利用各种语言的单语数据集。我们演示了在纯代码混合测试集上，这种单一脚本双语训练的效果很好。我们还通过 Tacotron2 + Waveglow 的设置对单说话人适应和多说话人训练进行了详尽的评估，结果显示前一种方法效果更好。我们还结合了迁移学习和仅解码器微调来提高性能。我们将这些方法与 Google TTS 进行了比较，使用我们提出的迁移学习方法获得了 CMOS 分数为 0.02。我们还进行了低资源语音适应实验，结果表明只需要 3 小时的数据就可以引入新语音。这凸显了我们预先训练模型在资源受限设置中的重要性。我们在大量的领域外纯代码混合句子上进行了主观评估，以展示系统的高质量。