🤖
A curated 18-month learning roadmap for becoming an AI Speech Engineer — covering foundations, core technologies (ASR, TTS, Speaker Verification, Diarization, Voice Conversion), …
An analysis of why language models hallucinate — hallucinations arise from statistical pressures in training and evaluation procedures that reward guessing over acknowledging …
Speaker Diarization answers "Who spoken when?" — covering core concepts, traditional and modern end-to-end approaches, and the latest Sortformer model for speaker segmentation.
Understanding entropy and why it's a core concept in decision trees, neural networks, and loss functions like cross-entropy.
Exploring LoRA-Whisper, a scalable and efficient approach for multilingual ASR using Low-Rank Adaptation to fine-tune OpenAI's Whisper model while avoiding catastrophic forgetting …