Muutke küpsiste eelistusi

E-raamat: Language Modeling for Automatic Speech Recognition of Inflective Languages: An Applications-Oriented Approach Using Lexical Data

,
Teised raamatud teemal:
  • Formaat - EPUB+DRM
  • Hind: 55,56 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Lisa ostukorvi
  • Lisa soovinimekirja
  • See e-raamat on mõeldud ainult isiklikuks kasutamiseks. E-raamatuid ei saa tagastada.
Language Modeling for Automatic Speech Recognition of Inflective Languages: An Applications-Oriented Approach Using Lexical DataSuurem pilt
Teised raamatud teemal:

DRM piirangud

  • Kopeerimine (copy/paste):

    ei ole lubatud

  • Printimine:

    ei ole lubatud

  • Kasutamine:

    Digitaalõiguste kaitse (DRM)
    Kirjastus on väljastanud selle e-raamatu krüpteeritud kujul, mis tähendab, et selle lugemiseks peate installeerima spetsiaalse tarkvara. Samuti peate looma endale  Adobe ID Rohkem infot siin. E-raamatut saab lugeda 1 kasutaja ning alla laadida kuni 6'de seadmesse (kõik autoriseeritud sama Adobe ID-ga).

    Vajalik tarkvara
    Mobiilsetes seadmetes (telefon või tahvelarvuti) lugemiseks peate installeerima selle tasuta rakenduse: PocketBook Reader (iOS / Android)

    PC või Mac seadmes lugemiseks peate installima Adobe Digital Editionsi (Seeon tasuta rakendus spetsiaalselt e-raamatute lugemiseks. Seda ei tohi segamini ajada Adober Reader'iga, mis tõenäoliselt on juba teie arvutisse installeeritud )

    Seda e-raamatut ei saa lugeda Amazon Kindle's. 

This book covers language modeling and automatic speech recognition for inflective languages (e.g. Slavic languages), which represent roughly half of the languages spoken in Europe. These languages do not perform as well as English in speech recognition systems and it is therefore harder to develop an application with sufficient quality for the end user. The authors describe the most important language features for the development of a speech recognition system. This is then presented through the analysis of errors in the system and the development of language models and their inclusion in speech recognition systems, which specifically address the errors that are relevant for targeted applications. The error analysis is done with regard to morphological characteristics of the word in the recognized sentences. The book is oriented towards speech recognition with large vocabularies and continuous and even spontaneous speech. Today such applications work with a rather small number of

languages compared to the number of spoken languages.

Introduction.- Speech Recognition in Inflective Languages.- Performance Evaluation Using Lexical Data.- Application Oriented Language Modeling.- An Example Application.- Conclusion.
1 Introduction
1(4)
1.1 Speech Recognition
1(2)
1.2 Performance in Specific Applications
3(1)
1.3 Organization of the Book
4(1)
2 Speech Recognition in Inflective Languages
5(26)
2.1 Basic Structure of a Speech Recognition System
5(1)
2.2 Acoustic Processing and Feature Extraction
5(2)
2.3 Acoustic Modeling
7(1)
2.4 Language Modeling
8(4)
2.4.1 Word Based n-Gram Models
8(2)
2.4.2 Smoothing and Back-Off
10(1)
2.4.3 Perplexity
11(1)
2.5 Search Algorithms
12(1)
2.6 Features of Inflective Languages
13(3)
2.6.1 Features of Slovene
15(1)
2.7 Language Modeling for Inflective Languages
16(6)
2.7.1 Vocabulary Size, Language Model Order and Corpus Size
16(2)
2.7.2 Subword Based Models
18(2)
2.7.3 Factored Language Models
20(1)
2.7.4 Other Methods
21(1)
2.8 Morphosyntactic Description Tagging
22(4)
2.8.1 Tagging Models
23(1)
2.8.2 Example
24(2)
2.9 Summary
26(5)
References
27(4)
3 Performance Evaluation Using Lexical Data
31(18)
3.1 Established Measures of Accuracy
31(2)
3.2 Alignment Issues of the Levenshtein Distance
33(1)
3.3 An Expanded Levenshtein Distance
34(3)
3.4 Error Analysis Example
37(1)
3.5 General Results
38(1)
3.6 Most Frequent Words and Lemmas
39(1)
3.7 Word Lengths
40(1)
3.8 Parts-of-Speech
40(3)
3.9 Word-Forms
43(1)
3.10 F-classes and Gender
43(2)
3.11 Summary
45(4)
References
46(3)
4 Application Oriented Language Modeling
49(16)
4.1 General Considerations
49(1)
4.2 A Weighted Word Error Rate
50(1)
4.3 Sample Applications
51(7)
4.3.1 Simple Speech Transcription
51(2)
4.3.2 Dictation System with Manual Correction
53(1)
4.3.3 Recognition of Numerals
54(1)
4.3.4 Recognition of Proper Nouns
55(1)
4.3.5 Speech Translation
55(1)
4.3.6 Keyword Spotting in LVCSR Results
56(2)
4.4 A Procedure for Application Oriented Language Modeling
58(1)
4.5 Examples of Specific Language Modeling
59(3)
4.5.1 Spontaneous Speech
59(1)
4.5.2 Modeling Lemmas and MSD Tags
60(1)
4.5.3 Modeling Minor Parts of Speech and Other Short Words
61(1)
4.6 Summary
62(3)
References
62(3)
5 An Example Application
65
5.1 The Target Application
65(1)
5.2 Experimental Setup
66(1)
5.3 First Results
67(1)
5.4 Improving Results
68(1)
5.5 Language Model Adaptation
69(2)
5.6 Conclusion
71
References
71
Lisainfo e-raamatute kohta Lisainfo e-raamatute kohta
Püsilink: https://www.kriso.ee/db/97833194160766e.html
Märksõnad: