Jezik: | Slovenski jezik |
---|---|
Leto izida: | 2022 |
Tipologija: | 2.11 - Diplomsko delo |
Organizacija: | UL FRI - Fakulteta za računalništvo in informatiko |
Založnik: | [L. Končar] |
UDK: | 004.8(043.2) |
COBISS: | 102623747 |
Št. ogledov: | 104 |
Št. prenosov: | 51 |
Ocena: | 0 (0 glasov) |
Metapodatki: |
Sekundarni jezik: | Angleški jezik |
---|---|
Sekundarni naslov: | Deep learning for text-to-speech |
Sekundarni povzetek: | Text-to-speech (TTS) is useful in a variety of areas. With deep learning we can use any person's voice for TTS, if only we have a few minutes of recordings of their speech. Converting the recordings into a dataset useful for model training is time consuming, so we created software that makes this process easier. We then created models using Tacotron and two vocoders: Griffin-Lim and WaveRNN. In the end we performed a comparison of these two vocoders and found that Griffin-Lim is much faster at synthesizing speech than WaveRNN, but the quality of speech is significantly worse. |
Sekundarne ključne besede: | deep learning;text-to-speech;computer and information science;diploma;Globoko učenje (strojno učenje);Računalništvo;Univerzitetna in visokošolska dela; |
Vrsta dela (COBISS): | Diplomsko delo/naloga |
Študijski program: | 1000468 |
Konec prepovedi (OpenAIRE): | 1970-01-01 |
Komentar na gradivo: | Univ. v Ljubljani, Fak. za računalništvo in informatiko |
Strani: | 36 str. |
ID: | 14808613 |