GlottDNN - A full-band glottal vocoder for statistical parametric speech synthesis

Manu Airaksinen; Bajibabu Bollepalli; Lauri Juvela; Zhizheng Wu; Simon King; Paavo Alku

doi:10.21437/Interspeech.2016-342

GlottDNN - A full-band glottal vocoder for statistical parametric speech synthesis

Manu Airaksinen
, Bajibabu Bollepalli
, Lauri Juvela
, Zhizheng Wu
, Simon King
, Paavo Alku

Speech Communication Technology

University of Edinburgh

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

34 Citations (Scopus)

Abstract

GlottHMM is a previously developed vocoder that has been successfully used in HMM-based synthesis by parameterizing speech into two parts (glottal flow, vocal tract) according to the functioning of the real human voice production mechanism. In this study, a new glottal vocoding method, GlottDNN, is proposed. The GlottDNN vocoder is built on the principles of its predecessor, GlottHMM, but the new vocoder introduces three main improvements: GlottDNN (1) takes advantage of a new, more accurate glottal inverse filtering method, (2) uses a new method of deep neural network (DNN) -based glottal excitation generation, and (3) proposes a new approach of band-wise processing of full-band speech. The proposed GlottDNN vocoder was evaluated as part of a full-band state-of-the-art DNN-based text-to-speech (TTS) synthesis system, and compared against the release version of the original GlottHMM vocoder, and the well-known STRAIGHT vocoder. The results of the subjective listening test indicate that GlottDNN improves the TTS quality over the compared methods.

Original language	English
Title of host publication	Proceedings of the Annual Conference of the International Speech Communication Association
Subtitle of host publication	Interspeech'16, San Francisco, USA, Sept. 8-12, 2016
Publisher	International Speech Communication Association (ISCA)
Pages	2473-2477
Number of pages	5
Volume	08-12-September-2016
ISBN (Electronic)	978-1-5108-3313-5
DOIs	https://doi.org/10.21437/Interspeech.2016-342
Publication status	Published - 2016
MoE publication type	A4 Conference publication
Event	Interspeech - San Francisco, United States Duration: 8 Sept 2016 → 12 Sept 2016 Conference number: 17

Publication series

Name	Proceedings of the Annual Conference of the International Speech Communication Association
Publisher	International Speech Communications Association
ISSN (Print)	1990-9770
ISSN (Electronic)	2308-457X

Conference

Conference	Interspeech
Country/Territory	United States
City	San Francisco
Period	08/09/2016 → 12/09/2016

Keywords

Deep neural network
Glottal inverse filtering
Speech synthesis
Vocoder

Access to Document

10.21437/Interspeech.2016-342

Cite this

Airaksinen, M., Bollepalli, B., Juvela, L., Wu, Z., King, S., & Alku, P. (2016). GlottDNN - A full-band glottal vocoder for statistical parametric speech synthesis. In Proceedings of the Annual Conference of the International Speech Communication Association: Interspeech'16, San Francisco, USA, Sept. 8-12, 2016 (Vol. 08-12-September-2016, pp. 2473-2477). (Proceedings of the Annual Conference of the International Speech Communication Association). International Speech Communication Association (ISCA). https://doi.org/10.21437/Interspeech.2016-342

Airaksinen, Manu ; Bollepalli, Bajibabu ; Juvela, Lauri et al. / GlottDNN - A full-band glottal vocoder for statistical parametric speech synthesis. Proceedings of the Annual Conference of the International Speech Communication Association: Interspeech'16, San Francisco, USA, Sept. 8-12, 2016. Vol. 08-12-September-2016 International Speech Communication Association (ISCA), 2016. pp. 2473-2477 (Proceedings of the Annual Conference of the International Speech Communication Association).

@inproceedings{a38fc5d0ebb54a58ae5ca59f5575ae09,

title = "GlottDNN - A full-band glottal vocoder for statistical parametric speech synthesis",

abstract = "GlottHMM is a previously developed vocoder that has been successfully used in HMM-based synthesis by parameterizing speech into two parts (glottal flow, vocal tract) according to the functioning of the real human voice production mechanism. In this study, a new glottal vocoding method, GlottDNN, is proposed. The GlottDNN vocoder is built on the principles of its predecessor, GlottHMM, but the new vocoder introduces three main improvements: GlottDNN (1) takes advantage of a new, more accurate glottal inverse filtering method, (2) uses a new method of deep neural network (DNN) -based glottal excitation generation, and (3) proposes a new approach of band-wise processing of full-band speech. The proposed GlottDNN vocoder was evaluated as part of a full-band state-of-the-art DNN-based text-to-speech (TTS) synthesis system, and compared against the release version of the original GlottHMM vocoder, and the well-known STRAIGHT vocoder. The results of the subjective listening test indicate that GlottDNN improves the TTS quality over the compared methods.",

keywords = "Deep neural network, Glottal inverse filtering, Speech synthesis, Vocoder",

author = "Manu Airaksinen and Bajibabu Bollepalli and Lauri Juvela and Zhizheng Wu and Simon King and Paavo Alku",

year = "2016",

doi = "10.21437/Interspeech.2016-342",

language = "English",

volume = "08-12-September-2016",

series = "Proceedings of the Annual Conference of the International Speech Communication Association",

publisher = "International Speech Communication Association (ISCA)",

pages = "2473--2477",

booktitle = "Proceedings of the Annual Conference of the International Speech Communication Association",

address = "France",

note = "Interspeech ; Conference date: 08-09-2016 Through 12-09-2016",

}

Airaksinen, M, Bollepalli, B, Juvela, L, Wu, Z, King, S & Alku, P 2016, GlottDNN - A full-band glottal vocoder for statistical parametric speech synthesis. in Proceedings of the Annual Conference of the International Speech Communication Association: Interspeech'16, San Francisco, USA, Sept. 8-12, 2016. vol. 08-12-September-2016, Proceedings of the Annual Conference of the International Speech Communication Association, International Speech Communication Association (ISCA), pp. 2473-2477, Interspeech, San Francisco, California, United States, 08/09/2016. https://doi.org/10.21437/Interspeech.2016-342

GlottDNN - A full-band glottal vocoder for statistical parametric speech synthesis. / Airaksinen, Manu; Bollepalli, Bajibabu; Juvela, Lauri et al.
Proceedings of the Annual Conference of the International Speech Communication Association: Interspeech'16, San Francisco, USA, Sept. 8-12, 2016. Vol. 08-12-September-2016 International Speech Communication Association (ISCA), 2016. p. 2473-2477 (Proceedings of the Annual Conference of the International Speech Communication Association).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - GlottDNN - A full-band glottal vocoder for statistical parametric speech synthesis

AU - Airaksinen, Manu

AU - Bollepalli, Bajibabu

AU - Juvela, Lauri

AU - Wu, Zhizheng

AU - King, Simon

AU - Alku, Paavo

N1 - Conference code: 17

PY - 2016

Y1 - 2016

N2 - GlottHMM is a previously developed vocoder that has been successfully used in HMM-based synthesis by parameterizing speech into two parts (glottal flow, vocal tract) according to the functioning of the real human voice production mechanism. In this study, a new glottal vocoding method, GlottDNN, is proposed. The GlottDNN vocoder is built on the principles of its predecessor, GlottHMM, but the new vocoder introduces three main improvements: GlottDNN (1) takes advantage of a new, more accurate glottal inverse filtering method, (2) uses a new method of deep neural network (DNN) -based glottal excitation generation, and (3) proposes a new approach of band-wise processing of full-band speech. The proposed GlottDNN vocoder was evaluated as part of a full-band state-of-the-art DNN-based text-to-speech (TTS) synthesis system, and compared against the release version of the original GlottHMM vocoder, and the well-known STRAIGHT vocoder. The results of the subjective listening test indicate that GlottDNN improves the TTS quality over the compared methods.

AB - GlottHMM is a previously developed vocoder that has been successfully used in HMM-based synthesis by parameterizing speech into two parts (glottal flow, vocal tract) according to the functioning of the real human voice production mechanism. In this study, a new glottal vocoding method, GlottDNN, is proposed. The GlottDNN vocoder is built on the principles of its predecessor, GlottHMM, but the new vocoder introduces three main improvements: GlottDNN (1) takes advantage of a new, more accurate glottal inverse filtering method, (2) uses a new method of deep neural network (DNN) -based glottal excitation generation, and (3) proposes a new approach of band-wise processing of full-band speech. The proposed GlottDNN vocoder was evaluated as part of a full-band state-of-the-art DNN-based text-to-speech (TTS) synthesis system, and compared against the release version of the original GlottHMM vocoder, and the well-known STRAIGHT vocoder. The results of the subjective listening test indicate that GlottDNN improves the TTS quality over the compared methods.

KW - Deep neural network

KW - Glottal inverse filtering

KW - Speech synthesis

KW - Vocoder

UR - https://www.scopus.com/pages/publications/84994338062

U2 - 10.21437/Interspeech.2016-342

DO - 10.21437/Interspeech.2016-342

M3 - Conference article in proceedings

AN - SCOPUS:84994338062

VL - 08-12-September-2016

T3 - Proceedings of the Annual Conference of the International Speech Communication Association

SP - 2473

EP - 2477

BT - Proceedings of the Annual Conference of the International Speech Communication Association

PB - International Speech Communication Association (ISCA)

T2 - Interspeech

Y2 - 8 September 2016 through 12 September 2016

ER -

Airaksinen M, Bollepalli B, Juvela L, Wu Z, King S, Alku P. GlottDNN - A full-band glottal vocoder for statistical parametric speech synthesis. In Proceedings of the Annual Conference of the International Speech Communication Association: Interspeech'16, San Francisco, USA, Sept. 8-12, 2016. Vol. 08-12-September-2016. International Speech Communication Association (ISCA). 2016. p. 2473-2477. (Proceedings of the Annual Conference of the International Speech Communication Association). doi: 10.21437/Interspeech.2016-342

GlottDNN - A full-band glottal vocoder for statistical parametric speech synthesis

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this