Transformer Based Text To Speech Synthesis With Speaker Embedding Control

via “speaker-embedding-extraction-and-vectorization”

automatic-speech-recognition model by undefined. 1,02,42,383 downloads.

Unique: Uses a ResNet-based speaker encoder trained with contrastive learning (triplet loss) on 100K+ speakers, optimizing for speaker discrimination in high-dimensional space. Embeddings are normalized to unit length, enabling efficient cosine similarity computation.

vs others: Produces embeddings with 5-10% better speaker verification accuracy (EER) compared to i-vector and x-vector baselines due to modern deep learning architecture and larger training dataset.