24 speech recognizers encode phonemes at very different depths: 21% vs 49%
stanfordnlp · x · 2026-10-26
A study presented at EMNLP analyzed internal representations across 24 speech recognizers and found that AI doesn't hear the world like humans — or even like other AI. Phonemes were easiest to read out at about 21% of encoder depth on average for Conformers, versus 49% for Transformers, showing architecture-dependent encoding of speech information.
More from Research
- Loss curves show the right inductive bias buys a large training efficiency gap — mike64_t · 2026-10-26
- Fortnow asks when algorithmic results are plausibly optimal, from Metric TSP to matrix mult — fortnow · 2026-10-26
- Domingos Clashes With OpenAI's Brockman Over the Curse of Dimensionality — AlexTensor · 2026-10-26
- Research agenda for multi-agent swarms: 7 open alignment problems — ZhijingJin · 2026-10-26
- Mathematician skips the trauma logs, launches a course on computer-assisted problem solving — zakkohane · 2026-10-26
- Doctor argues tinnitus, untreatable for 50 years, is exactly where AI medicine should break through — LaCaipirinha · 2026-10-26