{"title":"探索基于因果单元(IPU)的端到端智能语音识别系统方法","authors":"Anusha Prakash, Hema A Murthy","doi":"arxiv-2409.11915","DOIUrl":null,"url":null,"abstract":"Sentences in Indian languages are generally longer than those in English.\nIndian languages are also considered to be phrase-based, wherein semantically\ncomplete phrases are concatenated to make up sentences. Long utterances lead to\npoor training of text-to-speech models and result in poor prosody during\nsynthesis. In this work, we explore an inter-pausal unit (IPU) based approach\nin the end-to-end (E2E) framework, focusing on synthesising\nconversational-style text. We consider both autoregressive Tacotron2 and\nnon-autoregressive FastSpeech2 architectures in our study and perform\nexperiments with three Indian languages, namely, Hindi, Tamil and Telugu. With\nthe IPU-based Tacotron2 approach, we see a reduction in insertion and deletion\nerrors in the synthesised audio, providing an alternative approach to the\nFastSpeech(2) network in terms of error reduction. The IPU-based approach\nrequires less computational resources and produces prosodically richer\nsynthesis compared to conventional sentence-based systems.","PeriodicalId":501284,"journal":{"name":"arXiv - EE - Audio and Speech Processing","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Exploring an Inter-Pausal Unit (IPU) based Approach for Indic End-to-End TTS Systems\",\"authors\":\"Anusha Prakash, Hema A Murthy\",\"doi\":\"arxiv-2409.11915\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Sentences in Indian languages are generally longer than those in English.\\nIndian languages are also considered to be phrase-based, wherein semantically\\ncomplete phrases are concatenated to make up sentences. Long utterances lead to\\npoor training of text-to-speech models and result in poor prosody during\\nsynthesis. In this work, we explore an inter-pausal unit (IPU) based approach\\nin the end-to-end (E2E) framework, focusing on synthesising\\nconversational-style text. We consider both autoregressive Tacotron2 and\\nnon-autoregressive FastSpeech2 architectures in our study and perform\\nexperiments with three Indian languages, namely, Hindi, Tamil and Telugu. With\\nthe IPU-based Tacotron2 approach, we see a reduction in insertion and deletion\\nerrors in the synthesised audio, providing an alternative approach to the\\nFastSpeech(2) network in terms of error reduction. The IPU-based approach\\nrequires less computational resources and produces prosodically richer\\nsynthesis compared to conventional sentence-based systems.\",\"PeriodicalId\":501284,\"journal\":{\"name\":\"arXiv - EE - Audio and Speech Processing\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - EE - Audio and Speech Processing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.11915\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - EE - Audio and Speech Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.11915","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Exploring an Inter-Pausal Unit (IPU) based Approach for Indic End-to-End TTS Systems
Sentences in Indian languages are generally longer than those in English.
Indian languages are also considered to be phrase-based, wherein semantically
complete phrases are concatenated to make up sentences. Long utterances lead to
poor training of text-to-speech models and result in poor prosody during
synthesis. In this work, we explore an inter-pausal unit (IPU) based approach
in the end-to-end (E2E) framework, focusing on synthesising
conversational-style text. We consider both autoregressive Tacotron2 and
non-autoregressive FastSpeech2 architectures in our study and perform
experiments with three Indian languages, namely, Hindi, Tamil and Telugu. With
the IPU-based Tacotron2 approach, we see a reduction in insertion and deletion
errors in the synthesised audio, providing an alternative approach to the
FastSpeech(2) network in terms of error reduction. The IPU-based approach
requires less computational resources and produces prosodically richer
synthesis compared to conventional sentence-based systems.