Language model and acoustic model information in probabilistic speech recognition

Ferretti, Marco; Maltese, Giulio; Scarci, Stefano

doi:10.1109/icassp.1989.266525

Cited by 7 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From (4), Ferretti et al defined the SDE parameter [3]. This tries to gather acoustic-context information by the use of the a posteriori probabilities given by acoustic modeling.…”

Section: Difficulty Measures For Speech Recognitionmentioning

confidence: 99%

“…Estimating SDD is easier than SDE [3] because of the a priori estimation of the acoustic probabilities P (a i jw) from the transcriptions of the words. SDD and SDE differ in the sense that the second parameter considers the actual recognition system implemented, while we have been assuming that the phonetic similarity between two elemental units can only be zero or one for SDD: Thus, we rename SDD as I SDD; ideal speech decoding difficulty, because the practical implementation of a speech recognition system, as in P P; is not considered.…”

Section: A Practical Speech Decoding Difficultymentioning

confidence: 99%

See 1 more Smart Citation

A transcription-based approach to determine the difficulty of a speech recognition task

Garcı́a

Rubio²,

Díaz-Verdejo³

et al. 1999

IEEE Trans. Speech Audio Process.

View full text Add to dashboard Cite

Abstract-A new parameter for estimating the difficulty of a continuous speech recognition task, called speech decoding difficulty, is presented in this work. It is obtained from the language model defined for the recognition task and the phonetic similarity between the transcriptions of the words that make up the vocabulary used. Two variants of the proposed task difficulty measure are introduced: ideal speech decoding difficulty (ISDD), which is uninfluenced by practical considerations on the recognition system implemented, and a second, more realistic variant, called practical speech decoding difficulty (PSDD) to study the performance of a specific recognition system when confronting a given task.

show abstract

“…From (4), Ferretti et al defined the SDE parameter [3]. This tries to gather acoustic-context information by the use of the a posteriori probabilities given by acoustic modeling.…”

Section: Difficulty Measures For Speech Recognitionmentioning

confidence: 99%

Section: A Practical Speech Decoding Difficultymentioning

confidence: 99%