Next: Index F
Up: Alphabetically partitioned index
Previous: Index D
- E1 (USA)
- Telephone interfaces | Planning for expansion
- ear-training
- Subjects
- echo
- Microphone interfaces | Telephone interfaces | Telephone interfaces | Recommendation: Requirement profiles | Microphone | List of recommendations | List of recommendations | Telephone recordings | Speech quality and conditions | Post-production parameters
- echo cancelling functions
- Telephone interfaces
- EER
- see equal error rate (EER)
- efficiency
- Amplitude distortions
- electrical characteristics
- Speech quality and conditions
- electroglottogram
- Speech corpora with few
- electromagnetic articulography (EMA)
- Electromagnetic articulography | Electromagnetic articulography
- electromyograph activity (EMG activity)
- Speech corpora with few
- electromyograph signal (EMG signal)
- Spoken language corpus | Recording in a studio | Multi-channel recording
- electropalatography
- Spoken Language corpus collection | Multi-channel recording | Electropalatography | Electropalatography | A caveat
- EM algorithm
- Goals of the chapter | Linear interpolation | Linear interpolation | Recommendations: m-gram language models | Grammar based language models | Linear interpolation | Linear interpolation | Linear interpolation
- emotion
- Speaker characteristics verification or | Recommendation: Requirement profiles | Spontaneous speech | Spontaneous speech | Stable / transient speaker | Pathological speech | Automatic gain control | Typology of applications | Functions of prosody | Judgment tests of prosody | Functional tests of prosody | Functional tests of prosody | Functional tests of prosody | Functional tests of prosody | Functional tests of prosody | Functional tests of prosody | Functional tests of prosody | Functional tests of prosody | Prosodic quality testing
- emotion-by-rule
- Functional tests of prosody | Functional tests of prosody | Functional tests of prosody
- emulation packages
- Host-computer interfaces
- energy threshold
- Signal-to-noise ratio | Diagnostic methods with a | Recogniser specific parameters
- environment
- Spoken Language standards and | Spoken Language resources | Spoken Language corpus collection | Physical characterisation and description | Speech recognition systems | Speech recognition systems | Speaker dependency | Speech training material | Channel adaptation/Environment adaptation | Channel adaptation/Environment adaptation | Microphone interfaces | Recommendation: Requirement profiles | Recommendation: Requirement profiles | Recommendation: Requirement profiles | Speaker-independent vs. speaker-dependent systems | Pathological speech | Introduction | Data collection dimensions | Clandestine microphone recordings | Recommendations | Visible recordings | Visible recordings | Recommendations | Environment: Studio vs. on | Recording in a studio | Recording on location | Recommendations | Equipment | Equipment | Equipment | Equipment | Recommendations | Recording device | Recording device | Introduction | The communication chain | The communication chain | Transducer characteristics | Transducer characteristics | Transducer characteristics | Recording environment | 4. Anechoic chamber | Environment characteristics | Artificial vs. natural environment | Visual environment | Miscellaneous environmental factors | Description of recording conditions | Description of recording conditions | Description of recording conditions | Recommendations on reproducibility | Modification of speech parameters | Simulation of environmental factors | Simulation of environmental factors | Recommendations | Transformation of speech databases | Typology of applications | On-site (local) applications | Recommendations | Recommendations on choice of | Segmental reference conditions | Functional laboratory tests | Field tests | Interactive complexity of dialogue | Multimodal dialogue systems including | Characterisation | Environment characterisation | Environment characterisation | Environment characterisation | Result corpus characterisation | Assessment metrics | Recommendations on evaluation methodology
- acoustic
- Speech quantity and quality | General remarks | Recording in a studio | The communication chain | Recording environment | 1. Laboratory room | 3. Recording studio | Simulation of environmental factors | Post-production parameters | Environment characterisation
- adverse
- Signal-to-noise ratio | Recording device | Speech quality and conditions | User characterisation
- anechoic chamber
- see anechoic chamber
- artificial vs. natural
- Artificial vs. natural environment | Recommendations on artificial vs.
- auditory
- Introduction | The communication chain | The communication chain | Auditory environment | Recommendations on the auditory | Simulation of environmental factors
- development
- Canned speech | Multi-linguality | Computer telephony integration
- familiar
- Different types of speech
- field
- see field | see field
- in-car
- The communication chain | Specifications for speech corpora | Recommendations on microphones
- laboratory
- see laboratory | see laboratory
- living
- Voice characteristics tests
- noisy
- see noise | see noise
- open
- Connectivity
- recommendations on recording environment
- Recommendations on the recording | Recommendations on the recording
- reverberant
- see reverberation
- speech assessment
- Specifications for speech corpora | Specifications for speech corpora
- studio
- see studio | see studio
- test
- The environment in which | The environment in which
- very quiet
- 2. Microphone | Recommendations on microphones | Recommendations on the auditory | Recommendations on the visual
- visual
- Introduction | The communication chain | The communication chain | Visual environment | Recommendations on the visual
- environmental control device
- Pathological speech
- epenthesis
- Pronunciation information
- equal error rate (EER)
- Threshold setting | Threshold setting | System operating characteristic | System operating characteristic | System operating characteristic | System operating characteristic | System operating characteristic | System operating characteristic | System operating characteristic | System operating characteristic | System characteristic modelling | System characteristic modelling | System characteristic modelling | System characteristic modelling | System characteristic modelling | System characteristic modelling | System characteristic modelling | System characteristic modelling | System characteristic modelling | 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 | Open-set identification | Open-set identification | Recommendations | Recommendations | Recommendations | Recommendations | Recommendations | Recommendations | Recommendations | Recommendations | Recommendations | Examples of speaker verification | Examples of speaker verification
- equal loudness contours
- Phones and sones
- equalisation techniques
- diffuse-field
- see headphone, diffuse-field equalised
- free-field
- see headphone, free-field equalisation
- Erlang
- System dimension configuration | System dimension configuration
- error rate
- Recommendation: Requirement profiles | Monitoring and validation | Formal definition | Sources of recognition errors | The performance measure as | Isolated word scoring | Isolated word scoring | Isolated word scoring | Connected or continuous word | Confusions | Confusions | Confusions | Confusions | Interactive complexity of dialogue | Requirements for WOZ simulations
- equal
- see equal error rate (EER)
- sentence
- Recognition score | Reference methods
- word
- Recognition score | Connected or continuous word | Reference methods | Reference methods
- ESPRIT
- EAGLES objectives | Spoken Language standards and | The ESPRIT SAM | The ESPRIT SAM | The EAGLES Spoken | Assessment of Spoken Language | Speech synthesis | Speech corpora with few | Spoken language lexical databases | Spoken language lexical databases | Pronunciation information | Modelling of the auditory | Recommendations on the auditory | Introduction | Technical set-up | Why speech output assessment? | Subjects | Grapheme-phoneme conversion | Segmental tests at the | Segmental tests at the | Conclusion: summary of test
- estimator
- Estimating means | Isolated word scoring | Isolated word scoring | Isolated word scoring | Isolated word scoring | Connected or continuous word
- EUROM-1
- The ESPRIT SAM | The reference material | Correcting errors in the | Corpora for speech recognition | Speech corpora with few | Laryngography | Diagnostic methods with a
- event-dependent speaker recognition system
- see speaker recognition system, event-dependent
- exchange
- Definitions | Definitions | Design by intuition | Design by intuition | Glass box assessment | Quantitative measures
- expectation-maximisation algorithm
- see EM algorithm
- exploitation phase
- Speech recognition systems | Training
- Exploratory Factor Analysis
- Functional adequacy and user
- external NLP module
- Language modelling
EAGLES SWLG SoftEdition, May 1997. Get the book...