Index D

damping distortion

see distortion, damping

DARPA

Standards and resources for | Spoken Language standards and | Lexica in selected spoken | Experimental design of large | Background | Background

data model

Lexicon models and lexical | Lexicon models and lexical

database management

About this chapter | Scope

database management system (DBMS)

Speaker database | Spoken language lexicon formalisms | Lexicon architecture and lexical | Scoring the results | Basic statisticsANOVA

DATR

Spoken language lexical databases | Spoken language lexical databases | A simple sign model | Prosodic information | Spoken language lexicon formalisms | Spoken language lexicon formalisms

decibel scale

The dB scale | The dB scale | The dB scale

declarative knowledge base

Basic features of a

default inheritance hierarchy

Lexicon models and lexical

deletion

Sociolinguistic research | Pathological speech | Segmentation and labelling in | Segmentation and labelling in | Segmentation and labelling in | Segmentation and labelling in | Segmentation and labelling in | Orthographic transcription of read | Broad phonetic or phonotypic | Broad phonetic or phonotypic | Broad phonetic or phonotypic | Non-linguistic and other phenomena | Non-linguistic and other phenomena | Non-linguistic and other phenomena | List of recommendations | Lexica in selected spoken | Lexica in selected spoken | Pronunciation information | Idiomatic information | A simple database type: | Search: Word graphs | Search: Word graphs | Progress | Progress | Progress | Progress | Isolated word scoring | Isolated word scoring | Isolated word scoring | Connected or continuous word | Confusions | Confusions | Scoring method | Scoring method | Word stress | Segmental tests at the

demisyllable

Applications of morphology | Bayes decision rule | Experimental selection of material | Recommendations on choice of

dependable speaker

see speaker, dependable

dependent variable

see variable, dependent

derivation

Kinds of lexical unit | Prosodic information | Types of morphological information | Types of morphological information | Types of morphological information | Types of morphological information | Types of morphological information | Applications of morphology | Applications of morphology | Applications of morphology | Applications of morphology | Applications of morphology | Applications of morphology

derivational affixation

Applications of morphology

design

by intuition

Design by intuition | Design by intuition

by observation

Design by observation | Design by observation

by simulation

Design by simulation | WOZ conclusions

development test

Training | Training | Training | Experimental design of large | Development test | Development test | Dry run | Dry run

devoicing

Narrow phonetic transcription | Pronunciation information

diagnostic approach

Spoken Language resources | Assessment of recognition systems | Speech quality and conditions | Assessment purpose versus methodology | Assessment purpose versus methodology | Assessment purpose versus methodology | Recognition score | Specific calibrated databases | Diagnostic methods with a | Diagnostic methods with a | Assessment parameters | Assessment parameters | Assessment parameters | Test material selection | Test material selection | Test material selection | Speech quantity and variety | Scoring procedures | False acceptance rates and | Threshold setting | Why speech output assessment? | Users of this chapter | Users of this chapter | Users of this chapter | Glass box vs. black | Recommendations on choice of | Recommendations on choice of | Recommendations on choice of | Test procedures | Test procedures | Test procedures | Test procedures | Test procedures | Test procedures | Reference conditions | Acoustic aspects | Segmental tests | Segmental tests at the | Segmental tests at the | Segmental tests at the | Segmental tests at the | Segmental tests at the | Segmental tests at the | Segmental tests at the | Segmental tests at the | Segmental tests at the | Segmental tests at the | Segmental tests at the | Segmental tests at the | Segmental tests at the | Segmental tests at the | Segmental tests at the | Recommendations on specific segmental | Judgment tests of prosody | Voice characteristics tests | Voice characteristics tests | Voice characteristics tests | Voice characteristics tests | From human to automated | Predicting functional behaviour from | Segmental quality testing | Voice characteristics testing | SAM Standard Segmental | CLuster IDentification Test (CLID) | The Bellcore Test | Diagnostic Rhyme Test (DRT) | Modified Rhyme Test (MRT) | SAM Prosodic Form | SAM Prosodic Function

diagnostic corpora

Spoken Language resources | Manipulatedartificial and diagnostic | Manipulatedartificial and diagnostic

Diagnostic Pairs Sentence Intelligibility Evaluation Test (DPSIE)

Segmental tests at the | Segmental tests at the | Segmental tests at the | Segmental tests at the

Diagnostic Rhyme Test (DRT)

Diagnostic methods with a | Human calibration | Test procedures | Segmental tests at the | Segmental tests at the | Segmental tests at the | Segmental tests at the | Segmental tests at the | Segmental tests at the | Segmental tests at the | Segmental tests at the | Segmental tests at the | Segmental tests at the | Segmental tests at the | Segmental tests at the | Segmental quality testing | Diagnostic Rhyme Test (DRT)

dialect

Recommendation: Requirement profiles | Speaker-independent vs. speaker-dependent systems | Geographical and sociolinguistic factors | Geographical and sociolinguistic factors | Geographical and sociolinguistic factors | Geographical and sociolinguistic factors | Geographical and sociolinguistic factors | Geographical and sociolinguistic factors | Geographical and sociolinguistic factors | Geographical and sociolinguistic factors | Geographical and sociolinguistic factors | Geographical and sociolinguistic factors | Geographical and sociolinguistic factors | Geographical and sociolinguistic factors | Geographical and sociolinguistic factors | Geographical and sociolinguistic factors | Geographical and sociolinguistic factors | Geographical and sociolinguistic factors | Geographical and sociolinguistic factors | Geographical and sociolinguistic factors | Geographical and sociolinguistic factors | Geographical and sociolinguistic factors | Geographical and sociolinguistic factors | Geographical and sociolinguistic factors | Geographical and sociolinguistic factors | Geographical and sociolinguistic factors | Geographical and sociolinguistic factors | Geographical and sociolinguistic factors | Recording on location | Dialect forms | Dialect forms | List of recommendations | Prosodic information | Pragmatic information | Representative databases | Pre-production parameters | Pre-production parameters | Assessment parameters | Recommendations | Recommendations on choice of | Functions of voice characteristics | Voice characteristics tests | Design by observation | Design by observation | Design by observation | Subject variables | Subject variables

dialectology

Sociolinguistic research | Geographical and sociolinguistic factors | Geographical and sociolinguistic factors | Geographical and sociolinguistic factors | Introduction

dialogue

menu-driven

Branching factor (perplexity | Menu-driven systems | Menu dialogue systems | Menu dialogue systems

transcription of

Transcription of dialogues | Transcription of dialogues | List of recommendations

dialogue duration

A core set of | Dialogue duration | Dialogue duration | Transaction success | Transaction success

dialogue grammar

Specification and design | Evaluation | Knowledge databases

dialogue history

Interactive complexity of dialogue | Spoken language dialogue systems

dialogue manager

Branching factor (perplexity | Sophisticated dialogue manager | Sophisticated dialogue manager | Error recovery strategy | Routing to an operator | Definitions | Definitions | Interactive complexity of dialogue | Interactive complexity of dialogue | Multimodal dialogue systems including | Specification and design | Design by observation | Wizard variables | Wizard variables | Glass box assessment

dialogue model variables

see variables, dialogue model

dialogue strategies

Designing new systems | Subject variables | Dialogue strategies | Dialogue strategies

adaptive

Dialogue strategies

constitutive

Dialogue strategies

cooperative

Dialogue strategies

deterministic

Dialogue strategies

dialogue system

Introduction | Text-to-speech synthesis | Orthographic transcription of read | Lexica in selected spoken | Recommendations: m-gram language models | Recommendations: Language models and | How to read this | Role of statistical analysis | Role of statistical analysis | What are speech output | What are speech output | Assessment of interactive systems | Readings in interactive dialogue

automatic

Goals of the chapter

interactive

Scope | Scope | Assessment of interactive systems to Assessment of interactive systems | Types of application for | Interactive dialogue systems | Acoustic-based measures | Purpose | Scope | Scope | Different needs addressed | Section summary | Section summary | Section summary | Section summary | Section summary | Interactive dialogue systems | Multimodal dialogue systems including | Specification and design | Specification and design | Design by observation | Evaluation | Evaluation | User characterisation | Glass box assessment | Black box assessment | Black box assessment | Recommendations on evaluation methodology | Recommendations on evaluation methodology | Readings in interactive dialogue

vs. command system

Interactive dialogue systems compared | Interactive dialogue systems compared

menu

Branching factor (perplexity | Menu dialogue systems | Menu dialogue systems | Design by intuition | Design by simulation

multimodal

Multimodal dialogue systems including | Multimodal dialogue systems including

spoken language

Spoken Language systems | Scope | Interaction with an information | Spoken language and written | Pragmatic information | Spoken language dialogue systems | Spoken language dialogue systems | Specification and design | Design by intuition | Design by observation | Design by observation | Design by observation | WOZ conclusions | Iterative design methodology for | Additional recommendations | Readings in interactive dialogue | Evaluation | Contextual appropriateness | Readings in interactive dialogue

dictation

Standards and resources for | Coordination with other bodies | Speaking fluency | Visible recordings | Read speech recordings | Types of application for | Spoken language and written | Lexical semantic information | Goals of the chapter | Implications of the perplexity | Recommendations | Cache | Recommendations: m-gram language models | Search: Finding the single | Classification of recognition systems | Assessment parameters | Language model

dictionary

Spoken Language lexica | Lexicon size | Field speech data | Training | Adding / Removing speakers | Linguistic part | Reduced word forms | Spoken language and written | Spoken language and written | Basic lexicographic coverage criteria | Statistical language models | Extensions of the perplexity | Training material | Lexicon | Lexicon | Scoring method | Scoring method | Grapheme-phoneme conversion | Morphological decomposition

Duden

Reduced word forms | Dialect forms | Spoken language lexical databases | Lexica in selected spoken

exceptions

Word stress | Morphological decomposition

of phonetic elements

Read aloud isolated words | Speech corpora with few

on-line pronouncing

Orthographic transcription as the

Oxford English Dictionary

Spoken language lexical databases

phonemic

Orthographic transcription as the

phonetic

Linguistic part

pronouncing

Grapheme-phoneme conversion | Linguistic testing: Creating test

pronunciation

Spoken language lexical databases | Lexica in selected spoken | Lexica in selected spoken | Lexica in selected spoken | Bayes decision rule | Bayes decision rule

Digital Audio Tape (DAT)

Analog and digital speech | Data collection | Data collection | Data collection | Recommendations on data collection

digital signal

Telephone interfaces | Telephone interfaces | Telephone interfaces | Telephone interfaces | Telephone interfaces | Speech recordingstorage, and | Connectivity | Analog and digital speech | Quantisation and coding | Telephone recordings | Telephone recordings | Data collection | Data collection | Data collection | Data collection | Recommendations on the recording | Recommendations on data collection | Recommendations on data collection | Amplitude distortions | Amplitude distortions | Recommendations on recording chain | Description of recording conditions | Description of recording conditions | Analysis and conditioning tools | Hardware devices | Software tools | Software tools | Technical set-up | Addition of noise | Addition of noise | Addition of noise | Addition of noise | Automatic gain control | Examples of speaker verification

dimensions of difficulty

System capability profile versus

diphone

Phonetic part | Recommendation: Requirement profiles | Speech synthesis | Speech synthesis | Speech synthesis | Speech synthesis | Speech synthesis | Read aloud isolated sentences | Read aloud isolated sentences | Speech corpora with few | Lexical databases and system | Applications of morphology | Corpora | Corpora | Stochastic language modelling | Experimental selection of material | Experimental selection of material | Experimental selection of material | Experimental selection of material | Experimental selection of material | Experimental selection of material | Experimental selection of material | Experimental selection of material | Experimental selection of material | Experimental selection of material | Experimental selection of material | Experimental selection of material | Glass box vs. black | Subjects | Subjects | Recommendations on choice of | Segmental tests at the | Segmental tests at the | Segmental tests at the | Segmental tests at the | Functional tests of prosody | Functional tests of prosody | Functional tests of prosody | Functional tests of prosody | Functional tests of prosody | Functional tests of prosody | Functions of voice characteristics | Voice characteristics tests | Voice characteristics tests | Voice characteristics tests | Voice characteristics tests

Diphone Test

Segmental tests at the | Segmental tests at the | Segmental tests at the | Segmental tests at the | Segmental tests at the

diphthong

Introduction | Automatic and semi-automatic segmentation | Pronunciation information

disambiguation

Lexical information as properties | Recommendations on choice of | Syntactic parsing | Functional tests of prosody | Functional tests of prosody

discounting

absolute

Goals of the chapter | Problem formulation | Absolute discounting and backing-off | Absolute discounting and backing-off | The full trigram model | The full trigram model | Pooling of parameters | Pooling of parameters | Experimental results | Experimental results | Experimental results | Experimental results | Experimental results | Recommendations: m-gram language models | Absolute discounting and backing-off | Absolute discounting and backing-off

linear

Goals of the chapter | Problem formulation | Linear discounting and backing-off | Linear discounting and backing-off | Linear interpolation | Absolute discounting and backing-off | Absolute discounting and backing-off | Pooling of parameters | Experimental results | Experimental results | Experimental results | Experimental results | Linear discounting and backing-off | Linear discounting and backing-off | Linear interpolation | Absolute discounting and backing-off | Absolute discounting and backing-off

discourse analysis

General linguistic research | Spontaneous speech about a

distortion

Speech recognition systems | Microphone interfaces | Telephone interfaces | Recommendation: Requirement profiles | Audiology | Pathological speech | Pathological speech | Quantisation and coding | 5. Pressure zone microphones | 3. Microphone preamplifier | Telephone recordings | Telephone recordings | Recommendations on the recording | Recording chain characteristics | Recording chain characteristics | Signals and systems | Linear distortions | Non-linear distortions | Listener method | Recommendations | Human vs. automated | Overall quality reference conditions

amplitude

Amplitude distortions | Amplitude distortions

damping

Amplitude distortions | Amplitude distortions

linear

Introduction | 2. Soundproof booth | Linear distortions | Phase distortions | Recommendations on recording chain

non-linear

Introduction | Telephone recordings | Non-linear distortions | Non-linear distortions | Recommendations on recording chain

phase

Microphone | Data collection | Recommendations on data collection | Linear distortions | Phase distortions | Phase distortions

disyllable

Comparability across languages

documentation

Spoken language corpus | Spoken language corpus | Spoken language corpus | Reduced word forms | Interjections

domain

Classification of recognition systems

domain expertise

Subject variables | User characterisation

Doug Paul

Language model

DPSIE

see Diagnostic Pairs Sentence Intelligibility Evaluation Test

drivers

Drivers | Application programming interfaces (APIs) | Application generators | Recommendation: Requirement profiles

drop-out

Speech quality and conditions

DRT

see Diagnostic Rhyme Test (DRT)

dry run

Experimental design of large | Dry run\indexdry run | Dry run

DTMF

Telephone interfaces | Telephone interfaces | Speech recordingstorage, and | Interactive voice systems | DTMF\indexDTMFpulse detection\indexpulse detection, | DTMFpulse detection, | Examples of speaker verification | Definitions | Definitions

dummy head

1. Equalising headphones | 3. Using dummy heads | 3. Using dummy heads

dummy item

Recommendations

duration

Speech quantity and quality | Speech quantity and quality | Factorial experiments and corpus | Use of segmented speech | Automatic and semi-automatic segmentation | Types of approach to | Examples of the two | The ToBI labelling system | List of recommendations | List of recommendations | List of recommendations | Non-parametric tests | Classification | Acoustic-based measures | Judgment tests of prosody | From human to automated | Transaction success

dialogue

System dimension configuration | Spontaneous dialogue recordings | A core set of | Dialogue duration | Dialogue duration | Transaction success

mean vowel

Simple hypothesis testing

of a call

System dimension configuration | System dimension configuration

of a sentence

Types of language models

of average noise consumption

2. Hearing relevant habits

of recording

Random recordings | Cost

of training phase

Speaker-adapted systems | Speech training material | Lexicon generation

phoneme

Lexica in selected spoken | Recommendations on choice of | Functional tests of prosody

rule-derived

Judgment tests of prosody

segment

Examples of the two | Acoustic-based measures | Recommendations on choice of | Recommendations on choice of | Functions of segments | Judgment tests of prosody | Judgment tests of prosody | Judgment tests of prosody | Segmental quality testing

syllable

1. Average level and | 1. Average level and | 2. Precision of articulation | Word stress

tone unit

Simple hypothesis testing | Simple hypothesis testing | Simple hypothesis testing | Simple hypothesis testing

turn

A core set of | Turn duration | Turn duration | Transaction success

duration model

Phonetic part

duration rules

Use of segmented speech | Recommendations on choice of | Judgment tests of prosody | Judgment tests of prosody | Judgment tests of prosody | Functional tests of prosody

duration structure

Recommendations on choice of

dynamic microphone

see microphone, dynamic

dynamic programming

Search: Finding the single | Search: Finding the single | Search: Finding the single | Search: Finding the single | Search: Finding the single | Search: Finding the single | Search: Finding the single | Search: Finding the single | Search: Word graphs | Search: Word graphs | Search: Word graphs

dynamic range

Recording on location | Equipment | Speech quality and conditions | Addition of noise

Dynamic Time Warping (DTW)

Speech recognition systems | Segmentation | Reference systems | Reference systems | Reference systems | Reference systems | Reference systems | From human to automated

dysarthria

Pathological speech

dysphonia

Pathological speech | Pathological speech