tacotron 2
TTS architecture with attention-based decoder
Episodes
-
#6582: Why Text-to-Speech and Speech-to-Text Aren't MirrorsOne second of speech takes 24,000 sequential decisions in WaveNet, while speech recognition throws away most of the audio signal. -
#2982: Why Your TTS Model Nails "Shabbat" but Not "Keren HishtalmutWhy multilingual TTS models handle loanwords but fail at niche vocabulary — and what you can do about it. -
#2914: Can AI Read the Room? TTS Prosody ExplainedCan TTS models truly infer emotion from text, or just mimic patterns? We break down the science of prosody.