HMM 기반의 한국어 합성음에 대한 PESQ 및 MOS 평가의 상관도 분석
Correlation Analysis of PESQ and MOS Evaluation for HMM-based Synthetic Korean Speech
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
The PESQ is an objective speech quality evaluation measure that is known to have a high correlation with a subjective speech quality measure such as MOS. To examine whether it could be useful as an objective quality measure of synthetic speech, we carried out both subjective evaluation tests with MOS and DMOS and an objective evaluation test with PESQ for HMM-based Korean synthetic speech signals and analyzed the correlation between them. Experimental results have shown that the PESQ has correlations of 0.87 with MOS and 0.92 with DMOS. It means that the PESQ holds much promise for evaluating the quality of synthetic Korean speech.
Abstract
The PESQ is an objective speech quality evaluation measure that is known to have a high correlation with a subjective speech quality measure such as MOS. To examine whether it could be useful as an objective quality measure of synthetic speech, we carried out both subjective evaluation tests with MOS and DMOS and an objective evaluation test with PESQ for HMM-based Korean synthetic speech signals and analyzed the correlation between them. Experimental results have shown that the PESQ has correlations of 0.87 with MOS and 0.92 with DMOS. It means that the PESQ holds much promise for evaluating the quality of synthetic Korean speech.
참고문헌 (13)
- 한국어 합성음평가 가이드라인, "조철우", 대한음성학회, ~ (2005)
- 양희식, "한국어 음성합성기 성능평가에 의한 합성 음질개선", 대한음성학회 학술대회지, pp.37~40 (2002)
- "ITU-T Recommendation (2001). “Perceptual evaluation of speech quality (PESQ): An objective method for end-to-end speech quality assessment of narrow-band telephone networks and speech codecs”, P.862, 02", ~ (2001)
- "HMM-based Speech Synthesis System"[URL]
- Kim, S. J., "HMM-based Korean speech synthesizer with two-band mixed excitation model for embedded applications", 박사, pp.2007
- 배재철, "HMM 기반의 한국어 음성합성", 신호처리합동학술대회 논문집, 통권 : 20, pp.144~ (2007)
- 김일환, "HMM 기반 한국어 음성합성에서 지속시간 제어를 통한 자연성 개선", 석사, 전자전기컴퓨터학부, pp.2008
- "ITU-T Recommendation (1996). “Methods for subjective determination of transmission quality”, P.800, 08", ~ (1996)
- Yang, W., "Performance of the modified Bark spectral Distortion as an objective speech quality measure", Proceedings of ICASSP, 통권 : 1, pp.541~544 (1998)
- "ITU-T Recommendation (1996). “Objective quality measurement of telephone-band (300-3400Hz)”, P.861, 08", ~ (1996)
- Kim, I.H., "Control of duration model in HMM-based Korean Sspeech synthesis", Speech Sciences, 15(4), pp.97~105 (2008)
- "ITU-T Recommendation (2001). “Perceptual evaluation of speech quality (PESQ): An objective method for end-to-end speech quality assessment of narrow-band telephone networks and speech codecs”, P.862, 02", ~ (2001)