Index A

A-law

Speech recordingstorage, and | Recording on location | Recommendations | Quantisation and coding | Telephone recordings | Data collection

accelerations and movements

Microphone interfaces

accent

Phonetic part | Phonetic part | The MARSEC labelling | Prosodic labelling in the | Prosodic labelling in the | Prosodic labelling in the | Prosodic labelling in the | Prosodic labelling in the | Lexical databases and system | Kinds of lexical unit | Pragmatic information | Idiomatic information | What are speech output | What are speech output | Global vs. analytic assessment | Grapheme-phoneme conversion | Syntactic parsing | Segmental tests at the | Functions of prosody | Functions of prosody | Judgment tests of prosody | Functions of voice characteristics | Voice characteristics tests | Voice characteristics tests | Voice characteristics tests | Voice characteristics tests | Linguistic testing: Creating test | Linguistic testing: Creating test | Linguistic testing: Creating test | Prosodic quality testing | Prosodic quality testing

foreign

Presentation | Typology of applications

in MARSEC

The MARSEC labelling

lexical

Linguistic part

phrase

The ToBI labelling system | Prosodic labelling in the | Prosodic labelling in the

pitch

The ToBI labelling system | The ToBI labelling system | The ToBI labelling system | Prosodic labelling in the | Prosodic labelling in the | Prosodic labelling in the | Prosodic labelling in the | Spoken language and written | Prosodic information

regional

Speaker dependency | Speaker dependency | Geographical and sociolinguistic factors | Orthographic transcription as the | 2. Miscellaneous descriptors | Speaker classification tasks | Typology of applications | Subject variables

sentence

Read aloud isolated sentences | Read aloud isolated sentences | Read aloud isolated sentences | Read aloud text fragments | Glass box vs. black | Sentence accent | Sentence accent

syntactic

Linguistic part

tonal

Pronunciation information | Prosodic information

accent identification

Speaker classification tasks

acceptable shortfalls

System capability profile versus

acceptance

Speaker identification versus speaker | Definitions | Example | Expected benefit | Threshold setting | Threshold setting | Threshold setting | System operating characteristic | System characteristic modelling | Open-set identification | Reference systems | Examples of speaker verification

acceptance threshold

Recogniser specific parameters

accuracy

Introduction | Lexica in selected spoken | Populationssamples and other | Segmentation | The performance measure as | Connected or continuous word | Reference methods | Assessment parameters | System characteristic modelling | System characteristic modelling | System characteristic modelling | System characteristic modelling | System characteristic modelling | System characteristic modelling | System characteristic modelling | System characteristic modelling | Example | Example | Example | Recommendations | Recommendations | Recommendations | Recommendations | Recommendations | System and product assessment | Segmental tests | Glass box assessment

of classification

Progress

of pitch determination

Male / female speakers

of pronunciation

Male / female speakers | Male / female speakers | Judgment laboratory tests

of segmentation

Manual segmentation | Manual segmentation | Automatic and semi-automatic segmentation | Broad phonetic or phonotypic | List of recommendations | Role of statistical analysis | Segmentation

of the MORPA module

Morphological decomposition

acoustic environment

see environment, acoustic

acoustic interface

Acoustic aspects | Relationships among tests

vs. linguistic interface

Linguistic vs. acoustic | Linguistic vs. acoustic

acoustic module

Text-to-speech synthesis | Acoustic module\indexacoustic module | Acoustic module | Acoustic module | Recommendation: Requirement profiles | Linguistic testing: Creating test

acoustic testing

Acoustic testing: Developments for | Overall quality testing

acronym

Text-to-speech synthesis | Linguistic part | Linguistic part | Linguistic part | Linguistic part | Eight main differences between | Kinds of lexical unit | Pre-processing | Pre-processing

action

Definitions | Definitions | Definitions | Definitions | Interactive dialogue systems compared | Interactive dialogue systems compared | Interactive complexity of dialogue | Specification and design | Glass box assessment

Adaptive Differential PCM (ADPCM)

Speech recordingstorage, and | Speech recordingstorage, and | Speech recordingstorage, and

adverse conditions

see environment, adverse

affix

Morphologicalsyntactic, semantic and | Lexical databases and system | Spoken language and written | A simple sign model | A simple sign model | Stem and morph lexica | Stem and morph lexica | Types of morphological information | Applications of morphology | Applications of morphology | Applications of morphology | Applications of morphology | Applications of morphology | Applications of morphology | Applications of morphology | Morphological decomposition | The Bellcore Test | The Bellcore Test

affricate

Pronunciation information | Progress

AGC

see automatic gain control

age

see speaker, age of

age identification

Speaker characteristics verification or | Speaker classification tasks | Applicationssystems and products

age verification

Speaker classification tasks | Definitions

agent

Definitions | Definitions | Definitions | Definitions | Definitions | Definitions | Interactive dialogue systems compared | Interactive dialogue systems compared | Interactive dialogue systems compared | Interactive dialogue systems compared

agglutinative language

Fully inflected form lexica | Applications of morphology

air-flow measurement

Air-flow measurements | Air-flow measurements

alignment

Connected or continuous word | Connected or continuous word | Connected or continuous word | Connected or continuous word | Scoring method | Scoring method | Scoring method | Scoring method | Scoring method | Scoring method | Scoring method | Scoring method

DTW

Segmentation | Segmentation

forced

The lexicon in spoken

label

Corpora

phoneme

Recognition score

phonetic

Scoring method

segmental

Recommendations on choice of | Prosodic quality testing

speaker

Related tasks

time

Levels and types of | Search: Finding the single | Search: Finding the single | Search: Finding the single | Search: Word graphs | Search: Word graphs | Search: Word graphs

word

Recognition score

allophone

Speech synthesis | Speech synthesis | Speech corpora with few | Narrow phonetic transcription | Lexica in selected spoken | Pronunciation information | Pronunciation information | Subjects | Subjects | Recommendations on choice of | Recommendations on choice of | Recommendations on choice of | From human to automated

allophone synthesis

Subjects | Recommendations on choice of | Recommendations on choice of | Recommendations on choice of | From human to automated

alternation

morphographemic

Stem and morph lexica

morphophonological

Stem and morph lexica | Applications of morphology | Applications of morphology | Applications of morphology | Applications of morphology

orthographic

Applications of morphology | Applications of morphology

amplitude distortion

see distortion, amplitude

amplitude-frequency curve

Amplitude distortions

Analysis of Variance (ANOVA)

Ratio of sample variances | Analysis of Variance\indexAnalysis of | Analysis of Variance | Analysis of Variance | Analysis of Variance | Analysis of Variance | Analysis of Variance | Analysis of Variance | Analysis of Variance | Analysis of Variance | Segmentation | Employing expert judgments to | Analysis of Variance design | Analysis of Variance design | Specific calibrated databases | Basic statisticsANOVA

analytic approach

Lexicon generation | Subjects | Subjects | Subjects | Recommendations on choice of | Judgment laboratory tests | Segmental tests at the | Judgment tests of prosody | Judgment tests of prosody | Voice characteristics tests | Predicting global from analytic | Predicting global from analytic

vs. global approach

Global vs. analytic assessment | Global vs. analytic assessment

anaphora

Sentence syntax information | Interactive complexity of dialogue | Spoken language dialogue systems | Glass box assessment

anechoic chamber

Speaker-independent vs. speaker-dependent systems | 4. Anechoic chamber | 4. Anechoic chamber | Studio | 2. Microphone | Recommendations on the recording | Auditory environment | Open vs. closed headphones | 1. Equalising headphones | Modelling of the auditory | Subject conditioning | Recommendations on the auditory | Recommendations on the visual | Description of recording conditions | Reference channels | Speech quality | Environment characterisation

ANN

see Artificial Neural Networks (ANNs)

annotation

Spoken Language systems | The ESPRIT SAM | Scope | Spoken Language resources | Spoken Language corpus representation | Extension of language base | Spoken language corpus | Spoken language corpus | Spoken language corpus | Spoken language corpus | Spoken language corpus | The different nature of | Geographical and sociolinguistic factors | Introduction | Introduction | Introduction | Orthographic transcription of read | Orthographic transcription of read | Physical transcription | Types of approach to | Types of approach to | Examples of the two | Examples of the two | Non-linguistic and other phenomena | Non-linguistic and other phenomena | Non-linguistic and other phenomena | Non-linguistic and other phenomena | List of recommendations | List of recommendations | Lexical databases and system | Lexical databases and system | Lexicon architecture and the | Lexicon architecture and the | Linguistic testing: Creating test | Linguistic testing: Creating test

levels of

Levels and types of | Levels and types of | Levels and types of | Recording script | Orthographic transcription as the

of dysfluencies

Orthographic transcription of read

prosodic

Orthographic identity and phonetic | Examples of the two | The MARSEC labelling | The MARSEC labelling

segmental

Types of approach to | Types of approach to

types of

Levels and types of

ANOVA

see Analysis of Variance (ANOVA)

antonymy

Lexical properties and lexical | Lexical properties and lexical | Lexical properties and lexical

aperiodic motion

Pathological speech | Periodic and aperiodic motion | Periodic and aperiodic motion

aphasia

see pathological speech, aphasia

API

see application programming interfaces (APIs)

applicant speaker

see speaker, applicant

application generator

Menu-driven systems | Application generators\indexapplication generator | Application generators | System simulation and prototyping | Statistical tools | Recommendation: Requirement profiles

application programming interfaces (APIs)

Application programming interfaces (APIs) | Application programming interfaces (APIs) | Application generators | Connectivity | Computer telephony integration | Computer telephony integration | Statistical tools | Recommendation: Requirement profiles

application requirements

System design | Introduction | Introduction | System capability profile versus | System capability profile versus | System capability profile versus | System capability profile versus | System capability profile versus | Speaker characteristics verification or

archiphoneme

Pronunciation information | A simple database type:

Army Brat

Geographical and sociolinguistic factors

ARPA

The Linguistic Data Consortium | Assessment of Spoken Language | Lexica in selected spoken | Experimental design of large | Experimental design of large | Experimental design of large | Training material | Language model | Language model | Dry run | Test material selection | Test material selection | Scoring method

Articulation Index

Human vs. automated

articulatory parameter

Multi-channel recording

Artificial Neural Networks (ANNs)

Speech recognition systems | Role of statistical analysis | Role of statistical analysis | Role of statistical analysis | Sampling | Biases | Estimating proportions | Non-parametric tests | Experimental selection of material | Classification | Baseline performance

artificial test signals

Assessment of recognition systems | Assessment purpose versus methodology | Assessment purpose versus methodology | Artificial test signals

aspiration

Segmentation and labelling in | Narrow phonetic transcription | Acoustic-phonetic transcription | Pronunciation information | Pronunciation information

assimilation

Canned speech | Read aloud isolated words | A caveat | Broad phonetic or phonotypic | Pronunciation information | Idiomatic information | Grapheme-phoneme conversion | Syntactic parsing | Linguistic testing: Creating test | Linguistic testing: Creating test

ATIS corpus

Corpora for speech recognition | Spoken language systems | Spontaneous speech about a | Random recordings | Introduction | Prosodic transcription | Non-linguistic and other phenomena | Non-linguistic and other phenomena | Non-linguistic and other phenomena | Non-linguistic and other phenomena

audio port

Connectivity

audiology

Audiology | Audiology

audiometry

Read aloud isolated sentences | Audiometric descriptors to Audiometric descriptors | Audiometric descriptors | 2. Speech audiometry

auditory environment

see environment, auditory

automated testing/assessment

Towards a taxonomy of | Introduction | From human to automated | From human to automated | From human to automated | From human to automated | From human to automated

vs. human subjects

Human vs. automated | Human vs. automated

automatic gain control

Telephone interfaces | Automatic gain control | Automatic gain control

automatic segmentation

see segmentation, automatic

average noise consumption

2. Hearing relevant habits