Speaker-independent neural formant synthesis

Pablo Perez Zarazaga, Zofia Malisz, Gustaf Eje, Lauri Juvela

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference article in proceedingsScientificvertaisarvioitu

Abstrakti

We describe speaker-independent speech synthesis driven by a small set of phonetically meaningful speech parameters such as formant frequencies. The intention is to leverage deep-learning advances to provide a highly realistic signal generator that includes control affordances required for stimulus creation in the speech sciences. Our approach turns input speech parameters into predicted mel-spectrograms, which are rendered into waveforms by a pre-trained neural vocoder. Experiments with WaveNet and HiFi-GAN confirm that the method achieves our goals of accurate control over speech parameters combined with high perceptual audio quality. We also find that the small set of phonetically relevant speech parameters we use is sufficient to allow for speaker-independent synthesis (a.k.a. universal vocoding).
AlkuperäiskieliEnglanti
OtsikkoProceedings of Interspeech 2023
KustantajaInternational Speech Communication Association (ISCA)
Sivumäärä5
DOI - pysyväislinkit
TilaJulkaistu - 2023
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaInterspeech - Dublin, Irlanti
Kesto: 20 elok. 202324 elok. 2023

Julkaisusarja

NimiInterspeech
KustantajaInternational Speech Communication Association
ISSN (elektroninen)2958-1796

Conference

ConferenceInterspeech
Maa/AlueIrlanti
KaupunkiDublin
Ajanjakso20/08/202324/08/2023

Sormenjälki

Sukella tutkimusaiheisiin 'Speaker-independent neural formant synthesis'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä