ADAPTIVE LEARNING OF HIDDEN MARKOV MODELS FOR EMOTIONAL SPEECH
An on-line unsupervised algorithm for estimating the hidden Markov models (HMM) parame-ters is presented. The problem of hidden Markov models adaptation to emotional speech is solved. To increase the reliability of estimated HMM parameters, a mechanism of forgetting and updating is proposed. A funct...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | Russian |
| Published: |
National Academy of Sciences of Belarus, the United Institute of Informatics Problems
2016-10-01
|
| Series: | Informatika |
| Online Access: | https://inf.grid.by/jour/article/view/152 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832543167376785408 |
|---|---|
| author | A. V. Tkachenia |
| author_facet | A. V. Tkachenia |
| author_sort | A. V. Tkachenia |
| collection | DOAJ |
| description | An on-line unsupervised algorithm for estimating the hidden Markov models (HMM) parame-ters is presented. The problem of hidden Markov models adaptation to emotional speech is solved. To increase the reliability of estimated HMM parameters, a mechanism of forgetting and updating is proposed. A functional block diagram of the hidden Markov models adaptation algorithm is also provided with obtained results, which improve the efficiency of emotional speech recognition. |
| format | Article |
| id | doaj-art-989c0ae8b4194e549e40122265c87e2d |
| institution | Kabale University |
| issn | 1816-0301 |
| language | Russian |
| publishDate | 2016-10-01 |
| publisher | National Academy of Sciences of Belarus, the United Institute of Informatics Problems |
| record_format | Article |
| series | Informatika |
| spelling | doaj-art-989c0ae8b4194e549e40122265c87e2d2025-02-03T11:51:49ZrusNational Academy of Sciences of Belarus, the United Institute of Informatics ProblemsInformatika1816-03012016-10-01032127151ADAPTIVE LEARNING OF HIDDEN MARKOV MODELS FOR EMOTIONAL SPEECHA. V. TkacheniaAn on-line unsupervised algorithm for estimating the hidden Markov models (HMM) parame-ters is presented. The problem of hidden Markov models adaptation to emotional speech is solved. To increase the reliability of estimated HMM parameters, a mechanism of forgetting and updating is proposed. A functional block diagram of the hidden Markov models adaptation algorithm is also provided with obtained results, which improve the efficiency of emotional speech recognition.https://inf.grid.by/jour/article/view/152 |
| spellingShingle | A. V. Tkachenia ADAPTIVE LEARNING OF HIDDEN MARKOV MODELS FOR EMOTIONAL SPEECH Informatika |
| title | ADAPTIVE LEARNING OF HIDDEN MARKOV MODELS FOR EMOTIONAL SPEECH |
| title_full | ADAPTIVE LEARNING OF HIDDEN MARKOV MODELS FOR EMOTIONAL SPEECH |
| title_fullStr | ADAPTIVE LEARNING OF HIDDEN MARKOV MODELS FOR EMOTIONAL SPEECH |
| title_full_unstemmed | ADAPTIVE LEARNING OF HIDDEN MARKOV MODELS FOR EMOTIONAL SPEECH |
| title_short | ADAPTIVE LEARNING OF HIDDEN MARKOV MODELS FOR EMOTIONAL SPEECH |
| title_sort | adaptive learning of hidden markov models for emotional speech |
| url | https://inf.grid.by/jour/article/view/152 |
| work_keys_str_mv | AT avtkachenia adaptivelearningofhiddenmarkovmodelsforemotionalspeech |