Presentation | 2019-12-06 [Poster Presentation] Time-Varying Complex AR speech analysis based on l2-norm regularization Keiichi Funaki, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Linear prediction (LP) is a mathematical operation estimating an all-pole spectrum from the speechsignal. It is an essential methodology in speech coding since LP coefficients can be determined using a smallamount of computation and quantized efficiently using vector quantization (VQ). l2-norm regularized LP (RLP) and context-aware time-regularized LP (TRLP) analysis have been proposed and shown to improve performance. The former one suppresses rapid spectral changes in the frequency domain and the latter one suppresses the rapidspectral changes in the time domain. In our previous study, we proposed the MMSE-based time-varying complexAR (TV-CAR) speech analysis that is the complex and time-varying version of the LP and recently offered theRLP-based TV-CAR analysis. In this paper, we propose the novel l2-norm regularized TV-CAR analysis based onnot only the TRLP but also the RLP, and the objective evaluation using F0 estimation applied with the estimatedcomplex residual signals shows that the proposed method performs best. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | AR speech analysis / time-varying and complex analysis / l2-norm regularization / time-regularized LP / F0 estimation |
Paper # | SP2019-41 |
Date of Issue | 2019-11-29 (SP) |
Conference Information | |
Committee | NLC / IPSJ-NL / SP / IPSJ-SLP |
---|---|
Conference Date | 2019/12/4(3days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | NHK Science & Technology Research Labs. |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | The 6th Natural Language Processing Symposium & The 21th Spoken Language Symposium |
Chair | Takeshi Sakaki(Hottolink) / / Hisashi Kawai(NICT) |
Vice Chair | Mitsuo Yoshida(Toyohashi Univ. of Tech.) / Kazutaka Shimada(Kyushu Inst. of Tech.) / / Akinobu Ri(Nagoya Inst. of Tech.) |
Secretary | Mitsuo Yoshida(Ryukoku Univ.) / Kazutaka Shimada(NTT) / / Akinobu Ri(Kyoto Univ.) / (Waseda Univ.) |
Assistant | Takeshi Kobayakawa(NHK) / Hiroki Sakaji(Univ. of Tokyo) / / Tomoki Koriyama(Univ. of Tokyo) / Yusuke Ijima(NTT) |
Paper Information | |
Registration To | Technical Committee on Natural Language Understanding and Models of Communication / Special Interest Group on Natural Language / Technical Committee on Speech / Special Interest Group on Spoken Language Processing |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | [Poster Presentation] Time-Varying Complex AR speech analysis based on l2-norm regularization |
Sub Title (in English) | |
Keyword(1) | AR speech analysis |
Keyword(2) | time-varying and complex analysis |
Keyword(3) | l2-norm regularization |
Keyword(4) | time-regularized LP |
Keyword(5) | F0 estimation |
1st Author's Name | Keiichi Funaki |
1st Author's Affiliation | University of the Ryukyus(Univ. of the Ryukyus) |
Date | 2019-12-06 |
Paper # | SP2019-41 |
Volume (vol) | vol.119 |
Number (no) | SP-321 |
Page | pp.pp.73-77(SP), |
#Pages | 5 |
Date of Issue | 2019-11-29 (SP) |