arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2407.13435cs.CLcs.LGcs.SDeess.AS
收藏

通过低投入数据策略提升印度TTS系统在实际应用中的词汇外性能

Enhancing Out-of-Vocabulary Performance of Indian TTS Systems for Practical Applications through Low-Effort Data Strategies

AI4Bharat, Indian Institute of Technology, Madras(AI4Bharat、马德拉斯印度理工学院)

Srija Anand, Praveen Srinivasa Varadhan, Ashwin Sankar, Giri Raju, Mitesh M. Khapra

AI总结:

针对低资源印度语言TTS系统词汇外性能差的问题,提出利用志愿者录制含未见双字母组单词的低成本数据策略,在不影响语音质量的前提下提升OOV性能。

摘要:

针对印地语和泰米尔语等低资源语言的公开TTS数据集通常包含10-20小时的数据,导致词汇覆盖不足。这一局限在下游应用中尤为明显,因为领域特定词汇与频繁的英语代码混合相结合,导致大量词汇外(OOV)单词出现。为了突出这一问题,我们创建了一个包含来自多个实际应用的OOV单词的基准。事实上,最先进的印地语和泰米尔语TTS系统在此OOV基准上表现不佳,如可懂度测试所示。为了提升模型的OOV性能,我们提出了一种低投入且经济可行的策略来获取更多训练数据。具体而言,我们建议使用志愿者而非高质量配音演员来录制包含训练数据中未见过的字符双字母组的单词。我们证明,使用此类廉价数据,模型在OOV单词上的性能得到提升,同时不影响语音质量和域内性能。

英文摘要:

Publicly available TTS datasets for low-resource languages like Hindi and Tamil typically contain 10-20 hours of data, leading to poor vocabulary coverage. This limitation becomes evident in downstream applications where domain-specific vocabulary coupled with frequent code-mixing with English, results in many OOV words. To highlight this problem, we create a benchmark containing OOV words from several real-world applications. Indeed, state-of-the-art Hindi and Tamil TTS systems perform poorly on this OOV benchmark, as indicated by intelligibility tests. To improve the model's OOV performance, we propose a low-effort and economically viable strategy to obtain more training data. Specifically, we propose using volunteers as opposed to high quality voice artists to record words containing character bigrams unseen in the training data. We show that using such inexpensive data, the model's performance improves on OOV words, while not affecting voice quality and in-domain performance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑