J
John Makhoul
Researcher at BBN Technologies
Publications - 171
Citations - 17402
John Makhoul is an academic researcher from BBN Technologies. The author has contributed to research in topics: Hidden Markov model & Word error rate. The author has an hindex of 46, co-authored 171 publications receiving 16971 citations. Previous affiliations of John Makhoul include Raytheon & Microsoft.
Papers
More filters
Journal ArticleDOI
Linear prediction: A tutorial review
TL;DR: This paper gives an exposition of linear prediction in the analysis of discrete signals as a linear combination of its past values and present and past values of a hypothetical input to a system whose output is the given signal.
Proceedings Article
A Study of Translation Edit Rate with Targeted Human Annotation
TL;DR: A new, intuitive measure for evaluating machine translation output that avoids the knowledge intensiveness of more meaning-based approaches, and the labor-intensiveness of human judgments is defined.
Proceedings ArticleDOI
Enhancement of speech corrupted by acoustic noise
TL;DR: This paper describes a method for enhancing speech corrupted by broadband noise based on the spectral noise subtraction method, which can automatically adapt to a wide range of signal-to-noise ratios, as long as a reasonable estimate of the noise spectrum can be obtained.
Journal ArticleDOI
Vector quantization in speech coding
John Makhoul,S. Roucos,H. Gish +2 more
TL;DR: This tutorial review presents the basic concepts employed in vector quantization and gives a realistic assessment of its benefits and costs when compared to scalar quantization, and focuses primarily on the coding of speech signals and parameters.
Performance measures for information extraction
TL;DR: An error measure is defined, the slot error rate, which combines the different types of error directly, without having to resort to precision and recall as preliminary measures.