Continuous Speech Recognition Using Segmental Neural Nets

Abstract

We present the concept of a "Segmental Neural Net" (SNN) for phonetic modeling in continuous speech recognition. The SNN takes as input all the frames of a phonetic segment and gives as output an estimate of the probability of each of the phonemes, given the input segment. By tak- ing into account all the frames of a phonetic seg- ment simultaneously, the SNN overcomes the well- known conditional-independence limitation of hid- den Markov models (HMM). However, the prob- lem of automatic segmentation with neural nets is a formidable computing task compared to HMMs. Therefore, to take advantage of the training and decoding speed of HMMs, we have developed a novel hybrid SNN/HMM system that combines the advantages of both types of approaches. In this hy- brid system, use is made of the N-best paradigm to generate likely phonetic segmentations, which are then scored by the SNN. The HMM and SNN scores are then combined to optimize performance. In this manner, the recognition accuracy is guaran- teed to be no worse than the HMM system alone.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1991
Accession Number
ADA460342

Entities

People

  • G. Zavaliagkos
  • J. Makhoul
  • Robert E. Schwartz
  • S. Austin

Organizations

  • BBN Technologies

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Abstracts
  • Accuracy
  • Algorithms
  • Artificial Intelligence Computing
  • Artificial Intelligence Software
  • Automated Speech Recognition
  • Availability
  • Computations
  • Computer Vision
  • Data Science
  • Dimensionality Reduction
  • Language
  • Natural Languages
  • Neural Networks
  • Recognition
  • Signal Processing
  • Training

Fields of Study

  • Engineering

Readers

  • Irregular Warfare and Special Operations Cyberspace Operations against Adversarial Threats.
  • Mycotoxin ecology in Amazonian ecosystems.
  • Speech Processing/Speech Recognition.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks