Acoustic backing-off as an implementation of missing feature theory

Speech Communication

Volumn 34, Issue 3, 2001, Pages 247-265

  De Veth, Johan ^a   Cranen, Bert ^a   Boves, Louis ^a  

^a RADBOUD UNIVERSITY NIJMEGEN   (Netherlands)

Author keywords

Acoustic backing off; Automatic speech recognition; Mismatched training test conditions; Missing feature theory

Indexed keywords

ACOUSTIC WAVES; SPEECH SYNTHESIS; STATISTICAL METHODS; VECTORS;

ACOUSTIC BACKING-OFF; LOCAL DISTANCE FUNCTIONS (LDF); MISSING FEATURE THEORY;

SPEECH RECOGNITION;

EID: 0035342413     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-6393(00)00037-6     Document Type: Article

References (19)

1. Recognising occluded speech
2. On the effects of varying filter bank parameters on isolated word recognition
3. The effects of selected signal processing techniques on the performance of a filter bank based isolated word recognizer
4. The Dutch Polyphone corpus
5. Channel normalization techniques for automatic speech recognition over the telephone
6. Missing feature theory in ASR: Make sure you miss the right type of features
7. Acoustic pre-processing for optimal effectivity of missing feature theory
8. Robust speech recognition based on multi-stream features
9. Principles of lexical language modeling for speech recognition
10. Using missing feature theory to actively select features for robust speech recognition with interruptions, filtering, and noise
11. Comparison of text-independent speaker recognition methods using VQ-distortion and discrete/continuous HMMs
12. Some solutions to the missing feature problem in data classification, with applications to noise robust ASR
13. On the decorrelation of filter-bank energies in speech recognition
14. Mathematical foundations of hidden Markov models
15. Multi-band speech recognition in noisy environments
16. Sub-band based recognition of noisy speech