Topic: speech recognition

We have entered a golden age of artificial intelligence research, driven mainly by the advances in the artificial neural networks over the last several decades. Applications of these techniques—to machine vision, speech recognition, autonomous vehicles, natural language, and many other domains—are coming so quickly that many observers predict that the long-elusive goal of “Artificial General Intelligence” (AGI) is within our grasp. However, we still cannot build a machine capable of building a nest, stalking prey, or loading a dishwasher. I will describe how evolution may have shaped the algor

Rhythms stretching across multiple interacting frequencies and spatial scales are ubiquitous in brain activity during complex cognitive tasks. Yet their functional significance is hotly debated between a structural epiphenomenon of brain activity and mechanisms implementing computations. Speech processing, with its temporal cadence and multi-scale of syntactic invariants (syllables, words), is a paradigmatic example where rhythms have been proposed to play a key role [1], with a speech-modulated hierarchical structure of intercoupled cortical oscillations correlating with successful comprehens

Our ability to perceive speech remains resilient to variations in voice, rate, and temporal interruptions. While inference models addressed the first two [1], the computational principles by which speech understanding remains impervious to temporal restructuring are largely unexplored. Previous studies indicated intriguing recoveries in comprehension when speech is temporally modulated [2-4]. We show that predictive coding, constrained by endogenous rhythms, accounts for these quizzical results and enables robust lexical speech recovery. We build upon the major hypotheses that the rhythmic st