Beam search pruning in speech recognition using a posterior probability-based confidence measure

Sherif Abdou, Michael S. Scordilis

Research output: Contribution to journalArticlepeer-review

47 Scopus citations


In this work we propose the early incorporation of confidence information in the decoding process of large vocabulary speech recognition. A confidence based pruning technique is used to guide the search to the most promising paths. We introduce a posterior probability-based confidence measure that can be estimated efficiently and synchronously from the available information during the search process. The accuracy of this measure is enhanced using a discriminative training technique whose objective is to maximize the discrimination between the correct and incorrect decoding hypotheses. For this purpose, phone-level confidence scores are combined to derive word level scores. Highly compact models that exhibit minimal degradation in performance are introduced. Experimental results using large speech corpora show that the proposed method improves both the decoding accuracy and the decoding time when compared to a baseline recognition system that uses a conventional search approach. Furthermore, the introduced confidence measures are well-suited for cross-task portability.

Original languageEnglish (US)
Pages (from-to)409-428
Number of pages20
JournalSpeech Communication
Issue number3-4
StatePublished - Apr 1 2004


  • Confidence measure
  • Discriminative training
  • Pruning
  • Speech recognition

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Experimental and Cognitive Psychology
  • Linguistics and Language


Dive into the research topics of 'Beam search pruning in speech recognition using a posterior probability-based confidence measure'. Together they form a unique fingerprint.

Cite this