Epoch Extraction from Allpass Residual of Speech Signals
Identification of epochs from speech signals is a prominent task in speech processing. In this paper, epoch extraction is attempted from phase spectrum of speech signals. The phase spectrum of speech is modelled as an allpass (AP) filter by minimizing entropy of energy in the associated error signal...
Published in: | 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) |
---|---|
Main Authors: | , |
Format: | Conference Object |
Language: | unknown |
Published: |
2014
|
Subjects: | |
Online Access: | http://raiith.iith.ac.in/1183/ https://doi.org/10.1109/ICASSP.2014.6853846 |
id |
ftiith:oai:raiith.iith.ac.in:1183 |
---|---|
record_format |
openpolar |
spelling |
ftiith:oai:raiith.iith.ac.in:1183 2023-05-15T15:01:43+02:00 Epoch Extraction from Allpass Residual of Speech Signals Vijayan, K Kodukula, Sri Rama Murty 2014 http://raiith.iith.ac.in/1183/ https://doi.org/10.1109/ICASSP.2014.6853846 unknown Vijayan, K and Kodukula, Sri Rama Murty (2014) Epoch Extraction from Allpass Residual of Speech Signals. In: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 4-9, May 2014, Florence; Italy;. Electricity Conference or Workshop Item PeerReviewed 2014 ftiith https://doi.org/10.1109/ICASSP.2014.6853846 2022-09-28T08:32:52Z Identification of epochs from speech signals is a prominent task in speech processing. In this paper, epoch extraction is attempted from phase spectrum of speech signals. The phase spectrum of speech is modelled as an allpass (AP) filter by minimizing entropy of energy in the associated error signal. The AP residual thus obtained contains prominent unambiguous peaks at epoch locations. These peaks in AP residual constitute a set of candidate epoch locations from which appropriate ones are identified using a dynamic programming algorithm. The proposed method is evaluated on a subset of CMU Arctic database and it is observed that it delivered better epoch extraction performance than the prominent speech events estimation method-DYPSA. In case of telephone channel speech, the proposed method significantly outperformed zero frequency resonator based method also Conference Object Arctic Research Archive of Indian Institute of Technology, Hyderabad (RAIITH) Arctic 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 1493 1497 |
institution |
Open Polar |
collection |
Research Archive of Indian Institute of Technology, Hyderabad (RAIITH) |
op_collection_id |
ftiith |
language |
unknown |
topic |
Electricity |
spellingShingle |
Electricity Vijayan, K Kodukula, Sri Rama Murty Epoch Extraction from Allpass Residual of Speech Signals |
topic_facet |
Electricity |
description |
Identification of epochs from speech signals is a prominent task in speech processing. In this paper, epoch extraction is attempted from phase spectrum of speech signals. The phase spectrum of speech is modelled as an allpass (AP) filter by minimizing entropy of energy in the associated error signal. The AP residual thus obtained contains prominent unambiguous peaks at epoch locations. These peaks in AP residual constitute a set of candidate epoch locations from which appropriate ones are identified using a dynamic programming algorithm. The proposed method is evaluated on a subset of CMU Arctic database and it is observed that it delivered better epoch extraction performance than the prominent speech events estimation method-DYPSA. In case of telephone channel speech, the proposed method significantly outperformed zero frequency resonator based method also |
format |
Conference Object |
author |
Vijayan, K Kodukula, Sri Rama Murty |
author_facet |
Vijayan, K Kodukula, Sri Rama Murty |
author_sort |
Vijayan, K |
title |
Epoch Extraction from Allpass Residual of Speech Signals |
title_short |
Epoch Extraction from Allpass Residual of Speech Signals |
title_full |
Epoch Extraction from Allpass Residual of Speech Signals |
title_fullStr |
Epoch Extraction from Allpass Residual of Speech Signals |
title_full_unstemmed |
Epoch Extraction from Allpass Residual of Speech Signals |
title_sort |
epoch extraction from allpass residual of speech signals |
publishDate |
2014 |
url |
http://raiith.iith.ac.in/1183/ https://doi.org/10.1109/ICASSP.2014.6853846 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic |
genre_facet |
Arctic |
op_relation |
Vijayan, K and Kodukula, Sri Rama Murty (2014) Epoch Extraction from Allpass Residual of Speech Signals. In: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 4-9, May 2014, Florence; Italy;. |
op_doi |
https://doi.org/10.1109/ICASSP.2014.6853846 |
container_title |
2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) |
container_start_page |
1493 |
op_container_end_page |
1497 |
_version_ |
1766333721895501824 |