AffectEcho: Speaker Independent and Language-Agnostic Emotion and Affect Transfer for Speech Synthesis
This addresses the need for more authentic and speaker-independent emotion control in text-to-speech systems, though it is incremental by building on existing embedding methods.
The paper tackled the problem of capturing nuanced emotions in speech synthesis by proposing AffectEcho, an emotion translation model that uses a Vector Quantized codebook with five intensity levels, achieving state-of-the-art results in emotion transfer while preserving speaker identity and style.
Affect is an emotional characteristic encompassing valence, arousal, and intensity, and is a crucial attribute for enabling authentic conversations. While existing text-to-speech (TTS) and speech-to-speech systems rely on strength embedding vectors and global style tokens to capture emotions, these models represent emotions as a component of style or represent them in discrete categories. We propose AffectEcho, an emotion translation model, that uses a Vector Quantized codebook to model emotions within a quantized space featuring five levels of affect intensity to capture complex nuances and subtle differences in the same emotion. The quantized emotional embeddings are implicitly derived from spoken speech samples, eliminating the need for one-hot vectors or explicit strength embeddings. Experimental results demonstrate the effectiveness of our approach in controlling the emotions of generated speech while preserving identity, style, and emotional cadence unique to each speaker. We showcase the language-independent emotion modeling capability of the quantized emotional embeddings learned from a bilingual (English and Chinese) speech corpus with an emotion transfer task from a reference speech to a target speech. We achieve state-of-art results on both qualitative and quantitative metrics.