VOWEL NON-VOWEL BASED SPECTRALWARPING AND TIME SCALE MODIFICATION FOR IMPROVEMENT IN CHILDREN’S ASR

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference contributionScientificvertaisarvioitu

18 Lataukset (Pure)

Abstrakti

Acoustic differences between children’s and adults’ speech causes the degradation in the automatic speech recognition system performance when system trained on adults’ speech and tested on children’s speech. The key acoustic mismatch factors are formant, speaking rate, and pitch. In this paper, we proposed a linear prediction based spectral warping method by using the knowledge of vowel and non-vowel regions in
speech signals to mitigate the formant frequencies differences between child and adult speakers. The proposed method gives 31% relative improvement over the baseline system. We have also investigated time scale modification using RTISILA and
SOLAFS algorithms and found that our proposed method performs better. Combining the proposed method with RTISILA and SOLAFS results in a further error rate reduction. The final combined system gives 49% relative improvement compared to the baseline system.
AlkuperäiskieliEnglanti
OtsikkoIEEE International Conference on Acoustics, Speech and Signal Processing
KustantajaIEEE
TilaHyväksytty/In press - 2021
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaIEEE International Conference on Acoustics, Speech and Signal Processing - Toronto, Kanada
Kesto: 6 kesäkuuta 202111 kesäkuuta 2021

Julkaisusarja

NimiProceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing
ISSN (painettu)1520-6149
ISSN (elektroninen)2379-190X

Conference

ConferenceIEEE International Conference on Acoustics, Speech and Signal Processing
LyhennettäICASSP
MaaKanada
KaupunkiToronto
Ajanjakso06/06/202111/06/2021

Sormenjälki

Sukella tutkimusaiheisiin 'VOWEL NON-VOWEL BASED SPECTRALWARPING AND TIME SCALE MODIFICATION FOR IMPROVEMENT IN CHILDREN’S ASR'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä