Continuous speech recognition by statistical methods

1976/01/01 by F. Jelinek · 7 citations
Computer Science · #Speech Recognition and Synthesis #Speech and Audio Processing #Advanced Data Compression Techniques

paper · doi:10.1109/proc.1976.10159

openalex publication_date 1976/01/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Statistical methods useful in automatic recognition of continuous speech are described. They concern modeling of a speaker and of an acoustic processor, extraction of the models' statistical parameters and hypothesis search procedures and likelihood computations of linguistic decoding. Experimental results are presented that indicate the power of the methods.

Citations

• Statistical Inference for Probabilistic Functions of Finite State Markov Chains
• Optimal decoding of linear codes for minimizing symbol error rate (Corresp.)
• A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains

Cited by

• Multi-Head Decoder for End-to-End Speech Recognition
• Machine Learning Paradigms for Speech Recognition: An Overview
• Developments and directions in speech recognition and understanding, Part 1 [DSP Education]
• Phoneme recognition using time-delay neural networks
• Moving Toward High Precision Dynamical Modelling in Hidden Markov Models
• End-to-End Neural Segmental Models for Speech Recognition
• Frederick Jelinek [wikipedia]