@inproceedings{BauerZalkowMuelleretal., author = {Bauer, Judith and Zalkow, Frank and M{\"u}ller, Meinard and Dittmar, Christian}, title = {Evaluating the Impact of Prosody Feature Normalization on the Controllability of Pitch in Speech Synthesis}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7097}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70976}, pages = {188 -- 195}, abstract = {Recent neural text-to-speech (TTS) models are able to synthesize highly natural speech signals using deep learning techniques. In practical applications, it can be desirable to have explicit control over the prosody (speech rate, fundamental frequency, and energy) of the synthesized speech. Such controllability can be achieved by adding prosody prediction modules, whose main purpose is to estimate plausible prosody features for each phoneme in the text input. This explicit modeling also allows for changing prosody features at inference time, consequently enabling the adjustment of the prosody in the synthesized audio. In this paper, we evaluate to which extent deliberate manipulation of such prosody features is reflected in the resulting speech audio. We focus particularly on changing the pitch (i.e., fundamental frequency) while applying different normalization strategies.}, language = {en} }