Papers by Rene Altrov
Audiobook Dialogues as Training Data for Conversational Style Synthetic Voices (2022.lrec-1)
Copied to clipboard
Liisi Piits, Hille Pajupuu, Heete Sahkai, Rene Altrov, Liis Ermus, Kairi Tamuri, Indrek Hein, Meelis Mihkla, Indrek Kiissel, Egert Männisalu, Kristjan Suluste, Jaan Pajupuu
| Challenge: | Synthetic voices are increasingly used in applications that require a conversational speaking style. |
| Approach: | They compare voices trained on audiobook character speech corpus, audiobook narrator speech corpu and neutral-style sentence-based corpus . they conclude that the character speech and neutral style corpus are more suitable . |
| Outcome: | The evaluation of voices trained on three corpora of equal size was conducted by voice chatbots . the results may have been confounded by the greater acoustic variability and poorer phonemic coverage . |