INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
We present a neural network- based text-to-speech (TTS) synthesis system that can synthesise spoken sounds in the voices of many speakers. Our system is made up of three independently trained components: a speaker encoder network that was trained on a speaker verification task using an independent dataset of noisy speech without transcripts from thousands of speakers to generate a fixed-dimensional embedding vector from only seconds of reference speech from a target speaker; a Tacotron- based sequence-to-sequence synthesis network that generates a model spectrogram from text, conditioned on the speaker embedding; and we show that the proposed model can transfer the discriminatively-trained speaker encoder' s knowledge of speaker variability to the multispeaker TTS challenge and synthesis authentic speech from speakers not observed during t r a i n i n g . To g e t t h e o p t i m u m
generalisation performance, we quantify the value of training the speaker encoder on a wide and varied speaker set. Finally, we demonstrate that randomly chosen speaker embeddings can synthesis speech in the voices of fresh speakers who are not comparable to those used in training, showing that the model has learnt a high- quality speaker representation.
Keywords:
Tacotron, spectrogram, TTS, embeddings.
Cite Article:
"Text-To-Speech Synthesizer and Voice Cloning using Generative Model", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.8, Issue 5, page no.b522-b531, May-2023, Available :http://www.ijnrd.org/papers/IJNRD2305167.pdf
Downloads:
000118757
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn