Shrikanth S. Narayanan

Diarization-derived features can rival complex speech embeddings in predicting language proficiency, making automated assessments more accessible and efficient.

Speech tokenizers, despite being crucial for multimodal LLMs, primarily capture phonetic information, creating a semantic mismatch with text-derived semantics that hinders performance.

Control the accent of your TTS output without needing any accented training data, by transferring accent characteristics from other languages.