Applying a speaker-dependent speech compression technique to concatenative TTS synthesizers

Chang Heon Lee, Sung Kyo Jung, Hong-Goo Kang

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

This paper proposes a new speaker-dependent coding algorithm to efficiently compress a large speech database for corpus-based concatenative text-to-speech (TTS) engines while maintaining high fidelity. To achieve a high compression ratio and meet the fundamental requirements of concatenative TTS synthesizers, such as partial segment decoding and random access capability, we adopt a nonpredictive analysis-by-synthesis scheme for speaker-dependent parameter estimation and quantization. The spectral coefficients are quantized by using a memoryless split vector quantization (VQ) approach that does not use frame correlation. Considering that excitation signals of a specific speaker show low intra-variation especially in the voiced regions, the conventional adaptive codebook for pitch prediction is replaced by a speaker-dependent pitch-pulse codebook trained by a corpus of single-speaker speech signals. To further improve the coding efficiency, the proposed coder flexibly combines nonpredictive and predictive type method considering the structure of the TTS system. By applying the proposed algorithm to a Korean TTS system, we could obtain comparable quality to the G.729 speech coder and satisfy all the requirements that TTS system needs. The results are verified by both objective and subjective quality measurements. In addition, the decoding complexity of the proposed coder is around 55% lower than that of G.729 annex A.

Original languageEnglish
Article number4067023
Pages (from-to)632-640
Number of pages9
JournalIEEE Transactions on Audio, Speech and Language Processing
Volume15
Issue number2
DOIs
Publication statusPublished - 2007 Feb 1

Fingerprint

synthesizers
coders
decoding
Decoding
coding
random access
requirements
vector quantization
compression ratio
Vector quantization
Parameter estimation
engines
Engines
coefficients
synthesis
predictions
pulses

All Science Journal Classification (ASJC) codes

  • Acoustics and Ultrasonics
  • Electrical and Electronic Engineering

Cite this

@article{2cf603c2853c4e8c8435de7ea2e152d4,
title = "Applying a speaker-dependent speech compression technique to concatenative TTS synthesizers",
abstract = "This paper proposes a new speaker-dependent coding algorithm to efficiently compress a large speech database for corpus-based concatenative text-to-speech (TTS) engines while maintaining high fidelity. To achieve a high compression ratio and meet the fundamental requirements of concatenative TTS synthesizers, such as partial segment decoding and random access capability, we adopt a nonpredictive analysis-by-synthesis scheme for speaker-dependent parameter estimation and quantization. The spectral coefficients are quantized by using a memoryless split vector quantization (VQ) approach that does not use frame correlation. Considering that excitation signals of a specific speaker show low intra-variation especially in the voiced regions, the conventional adaptive codebook for pitch prediction is replaced by a speaker-dependent pitch-pulse codebook trained by a corpus of single-speaker speech signals. To further improve the coding efficiency, the proposed coder flexibly combines nonpredictive and predictive type method considering the structure of the TTS system. By applying the proposed algorithm to a Korean TTS system, we could obtain comparable quality to the G.729 speech coder and satisfy all the requirements that TTS system needs. The results are verified by both objective and subjective quality measurements. In addition, the decoding complexity of the proposed coder is around 55{\%} lower than that of G.729 annex A.",
author = "Lee, {Chang Heon} and Jung, {Sung Kyo} and Hong-Goo Kang",
year = "2007",
month = "2",
day = "1",
doi = "10.1109/TASL.2006.876762",
language = "English",
volume = "15",
pages = "632--640",
journal = "IEEE Transactions on Speech and Audio Processing",
issn = "1558-7916",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

Applying a speaker-dependent speech compression technique to concatenative TTS synthesizers. / Lee, Chang Heon; Jung, Sung Kyo; Kang, Hong-Goo.

In: IEEE Transactions on Audio, Speech and Language Processing, Vol. 15, No. 2, 4067023, 01.02.2007, p. 632-640.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Applying a speaker-dependent speech compression technique to concatenative TTS synthesizers

AU - Lee, Chang Heon

AU - Jung, Sung Kyo

AU - Kang, Hong-Goo

PY - 2007/2/1

Y1 - 2007/2/1

N2 - This paper proposes a new speaker-dependent coding algorithm to efficiently compress a large speech database for corpus-based concatenative text-to-speech (TTS) engines while maintaining high fidelity. To achieve a high compression ratio and meet the fundamental requirements of concatenative TTS synthesizers, such as partial segment decoding and random access capability, we adopt a nonpredictive analysis-by-synthesis scheme for speaker-dependent parameter estimation and quantization. The spectral coefficients are quantized by using a memoryless split vector quantization (VQ) approach that does not use frame correlation. Considering that excitation signals of a specific speaker show low intra-variation especially in the voiced regions, the conventional adaptive codebook for pitch prediction is replaced by a speaker-dependent pitch-pulse codebook trained by a corpus of single-speaker speech signals. To further improve the coding efficiency, the proposed coder flexibly combines nonpredictive and predictive type method considering the structure of the TTS system. By applying the proposed algorithm to a Korean TTS system, we could obtain comparable quality to the G.729 speech coder and satisfy all the requirements that TTS system needs. The results are verified by both objective and subjective quality measurements. In addition, the decoding complexity of the proposed coder is around 55% lower than that of G.729 annex A.

AB - This paper proposes a new speaker-dependent coding algorithm to efficiently compress a large speech database for corpus-based concatenative text-to-speech (TTS) engines while maintaining high fidelity. To achieve a high compression ratio and meet the fundamental requirements of concatenative TTS synthesizers, such as partial segment decoding and random access capability, we adopt a nonpredictive analysis-by-synthesis scheme for speaker-dependent parameter estimation and quantization. The spectral coefficients are quantized by using a memoryless split vector quantization (VQ) approach that does not use frame correlation. Considering that excitation signals of a specific speaker show low intra-variation especially in the voiced regions, the conventional adaptive codebook for pitch prediction is replaced by a speaker-dependent pitch-pulse codebook trained by a corpus of single-speaker speech signals. To further improve the coding efficiency, the proposed coder flexibly combines nonpredictive and predictive type method considering the structure of the TTS system. By applying the proposed algorithm to a Korean TTS system, we could obtain comparable quality to the G.729 speech coder and satisfy all the requirements that TTS system needs. The results are verified by both objective and subjective quality measurements. In addition, the decoding complexity of the proposed coder is around 55% lower than that of G.729 annex A.

UR - http://www.scopus.com/inward/record.url?scp=57749176769&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=57749176769&partnerID=8YFLogxK

U2 - 10.1109/TASL.2006.876762

DO - 10.1109/TASL.2006.876762

M3 - Article

VL - 15

SP - 632

EP - 640

JO - IEEE Transactions on Speech and Audio Processing

JF - IEEE Transactions on Speech and Audio Processing

SN - 1558-7916

IS - 2

M1 - 4067023

ER -