Discriminative Learning for Speech Recognition: Theory and Practice - Xiadong He,Li Deng - cover
Discriminative Learning for Speech Recognition: Theory and Practice - Xiadong He,Li Deng - cover
Dati e Statistiche
Salvato in 0 liste dei desideri
Discriminative Learning for Speech Recognition: Theory and Practice
Disponibilità in 2 settimane
48,40 €
48,40 €
Disp. in 2 settimane

Descrizione


In this book, we introduce the background and mainstream methods of probabilistic modeling and discriminative parameter optimization for speech recognition. The specific models treated in depth include the widely used exponential-family distributions and the hidden Markov model. A detailed study is presented on unifying the common objective functions for discriminative learning in speech recognition, namely maximum mutual information (MMI), minimum classification error, and minimum phone/word error. The unification is presented, with rigorous mathematical analysis, in a common rational-function form. This common form enables the use of the growth transformation (or extended Baum–Welch) optimization framework in discriminative learning of model parameters. In addition to all the necessary introduction of the background and tutorial material on the subject, we also included technical details on the derivation of the parameter optimization formulas for exponential-family distributions, discrete hidden Markov models (HMMs), and continuous-density HMMs in discriminative learning. Selected experimental results obtained by the authors in firsthand are presented to show that discriminative learning can lead to superior speech recognition performance over conventional parameter learning. Details on major algorithmic implementation issues with practical significance are provided to enable the practitioners to directly reproduce the theory in the earlier part of the book into engineering practice. Table of Contents: Introduction and Background / Statistical Speech Recognition: A Tutorial / Discriminative Learning: A Unified Objective Function / Discriminative Learning Algorithm for Exponential-Family Distributions / Discriminative Learning Algorithm for Hidden Markov Model / Practical Implementation of Discriminative Learning / Selected Experimental Results / Epilogue / Major Symbols Used in the Book and Their Descriptions / Mathematical Notation / Bibliography

Dettagli

112 p.
Testo in English
235 x 191 mm
9783031014291
Informazioni e Contatti sulla Sicurezza dei Prodotti

Le schede prodotto sono aggiornate in conformità al Regolamento UE 988/2023. Laddove ci fossero taluni dati non disponibili per ragioni indipendenti da Feltrinelli, vi informiamo che stiamo compiendo ogni ragionevole sforzo per inserirli. Vi invitiamo a controllare periodicamente il sito www.lafeltrinelli.it per eventuali novità e aggiornamenti.
Per le vendite di prodotti da terze parti, ciascun venditore si assume la piena e diretta responsabilità per la commercializzazione del prodotto e per la sua conformità al Regolamento UE 988/2023, nonché alle normative nazionali ed europee vigenti.

Per informazioni sulla sicurezza dei prodotti, contattare productsafety@feltrinelli.it