Scaling laws in human speech, decreasing emergence of new words and a generalized model
Human language, as a typical complex system, its organization and evolution is an attractive topic for both physical and cultural researchers. In this paper, we present the first exhaustive analysis of the text organization of human speech. Two important results are that: (i) the construction and organization of spoken language can be characterized as Zipf's law and Heaps' law, as observed in written texts; (ii) word frequency vs. rank distribution and the growth of distinct words with the increase of text length shows significant differences between book and speech. In speech word frequency distribution are more concentrated on higher frequency words, and the emergence of new words decreases much rapidly when the content length grows. Based on these observations, a new generalized model is proposed to explain these complex dynamical behaviors and the differences between speech and book.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
The Quantization Model of Neural Scaling
We propose the Quantization Model of neural scaling laws, explaining both the observed power law dropoff of loss with model and data size, and also the sudden emergence of new capabilities with scale. We derive this mode…
Language ModelingLanguage ModellingmodelQuantizationScaling Properties of Continuous Diffusion Spoken Language Models
Speech-only spoken language models (SLMs) lag behind text and text-speech models in performance, with recent discrete autoregressive (AR) SLMs indicating significant computational and data demands to match text models. S…
Universal scaling laws rule explosive growth inhuman cancers
Most physical and other natural systems are complex entities composed of a large number of interacting individual elements. It is a surprising fact that they often obey the so-called scaling laws relating an observable q…
OWLS: Scaling Laws for Multilingual Speech Recognition and Translation Models
Neural scaling laws offer valuable insights for designing robust sequence processing architectures. While these laws have been extensively characterized in other modalities, their behavior in speech remains comparatively…
speech-recognitionSpeech RecognitionTranslationNeural Scaling Laws Rooted in the Data Distribution
Deep neural networks exhibit empirical neural scaling laws, with error decreasing as a power law with increasing model or data size, across a wide variety of architectures, tasks, and datasets. This universality suggests…
Language ModelingLanguage Modelling