메뉴 건너뛰기




Volumn , Issue , 1997, Pages 267-270

USEFULNESS OF PHONETIC PARAMETERS IN A REJECTION PROCEDURE OF AN HMM BASED SPEECH RECOGNITION SYSTEM

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTIC NOISE; ECONOMIC AND SOCIAL EFFECTS; SPEECH RECOGNITION;

EID: 85009136277     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper
Times cited : (10)

References (8)
  • 1
    • 0002267291 scopus 로고    scopus 로고
    • A Multi-level Model for Intonation Labels
    • Ostendorf M. and Ross K.: « A Multi-level Model for Intonation Labels», Computing Prosody, pp. 291-308, 1996.
    • (1996) Computing Prosody , pp. 291-308
    • Ostendorf, M.1    Ross, K.2
  • 2
    • 0030205397 scopus 로고    scopus 로고
    • Modelling of phone duration (using the TIMIT database) and its potential benefit for ASR
    • and al
    • Pols L. and al.: « Modelling of phone duration (using the TIMIT database) and its potential benefit for ASR», Speech Communication 19, pp: 161-176, 1996.
    • (1996) Speech Communication , vol.19 , pp. 161-176
    • Pols, L.1
  • 3
    • 85135179780 scopus 로고    scopus 로고
    • Accent Phrase Segmentation by F0 Clustering Using Superpositional Modelling
    • and al
    • Nakai M. and al.: «Accent Phrase Segmentation by F0 Clustering Using Superpositional Modelling», Computing Prosody, pp. 343-359, 1996.
    • (1996) Computing Prosody , pp. 343-359
    • Nakai, M.1
  • 4
    • 0026940228 scopus 로고
    • Use of minimum duration and energy contour for phonemes to improve large vocabulary isolated-word recognition
    • and al
    • Gupta V. and al.: « Use of minimum duration and energy contour for phonemes to improve large vocabulary isolated-word recognition», Computer Speech and Language, vol. 6, pp.345-359, 1993.
    • (1993) Computer Speech and Language , vol.6 , pp. 345-359
    • Gupta, V.1
  • 5
    • 85135161827 scopus 로고
    • Using Segmental Duration Prediction for Rescoring the N-best Solution in Speech Recognition
    • and al
    • Bartkova K. and al.: « Using Segmental Duration Prediction for Rescoring the N-best Solution in Speech Recognition», ICPhS95, Stockholm, Vol.4, pp:248-251, 1995.
    • (1995) ICPhS95, Stockholm , vol.4 , pp. 248-251
    • Bartkova, K.1
  • 6
    • 0029410152 scopus 로고
    • Operational and experimental French telecommunication services using CNET speech recognition and text-to-speech synthesis
    • and al
    • Sorin C. and al.: «Operational and experimental French telecommunication services using CNET speech recognition and text-to-speech synthesis», Speech Communication 17, pp:273-286, 1995.
    • (1995) Speech Communication , vol.17 , pp. 273-286
    • Sorin, C.1
  • 7
    • 84935527635 scopus 로고
    • On the modelisation of allophones in an HMM based speech recognition system
    • and al: Genova
    • Jouvet D. and al: « On the modelisation of allophones in an HMM based speech recognition system», EUROSPEECH, Genova, pp. 923-926, 1991.
    • (1991) EUROSPEECH , pp. 923-926
    • Jouvet, D.1
  • 8
    • 85135150959 scopus 로고    scopus 로고
    • Introduction de parametres phonetiques en post traitement d'un systeme markovien de reconnaissace de la parole
    • and al
    • Bartkova K. and al.: «Introduction de parametres phonetiques en post traitement d'un systeme markovien de reconnaissace de la parole», JEP Avignon, pp. 305-308, 1996.
    • (1996) JEP Avignon , pp. 305-308
    • Bartkova, K.1


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.