Search Results 1-20 of 37

  • 1 / 2
  • Stereophonic Music Separation Based on Non-Negative Tensor Factorization with Cepstral Distance Regularization

    SEKI Shogo , TODA Tomoki , TAKEDA Kazuya

    … To address this issue, this paper proposes a Cepstral Distance Regularization (CDR) method for NTF-based stereo channel separation, which involves making the cepstrum of the separated source signals follow Gaussian Mixture Models (GMMs) of the corresponding the music source signal. …

    IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E101.A(7), 1057-1064, 2018


  • A combined cepstral distance method for emotional speech recognition

    Quan Changqin , Zhang Bin , Sun Xiao , Ren Fuji

    … This article presents a combined cepstral distance method in two-group multi-class emotion classification for emotional speech recognition. … Cepstral distance combined with speech energy is well used as speech signal endpoint detection in speech recognition. … In this work, the use of cepstral distance aims to measure the similarity between frames in emotional signals and in neutral signals. …

    International Journal of Advanced Robotic Systems 14(4), 1-9, 2017-07-01


  • Analysis of effects of voice mimicry on speaker verification and acoustic features of the imitated voices  [in Japanese]

    IWANO Koji , SONE Taito , SAKAMOTO Kanako

    話者照合システムにおいて,物真似(模倣)攻撃に対する脆弱性を正しく把握し,その対応策を講じることは極めて重要である.本稿では,一般人(物真似の素人)を対象として模倣音声を収録し,それを用いて模倣行為で生じる音響特徴の変動の分析と,HMMに基づく話者照合システムの性能に与える影響の調査を行った.男女各6名の通常発声と模倣音声を用いて,模倣によるケプストラム特徴の変動分析を行ったところ,「模倣の努力に …

    IEICE technical report. Speech 114(411), 43-48, 2015-01-22

  • Evaluation of tooth-conduction microphone for communication under noisy environment

    Torikai Yusuke , Kuze Dai , Kurosawa Junko , Oikawa Yasuhiro , Yamasaki Yoshio

    … To evaluate articulation of TCV, we adopted monosyllable articulation for subjective assessment and linear predictive coding cepstral distance for objective assessment. …

    Acoustical Science and Technology 36(6), 500-506, 2015


  • Intra-speaker spectral parameter variation between utterances of the same sentence and its prediction  [in Japanese]

    INUKAI Tatsuo , TODA Tomoki , NEUBIG Graham , SAKTI Sakriani , NAKAMURA Satoshi

    統計的声質変換技術におけるスペクトルパラメータ変換処理おいて,その評価指標や変換モデルの学習指標として,しばしば変換パラメータと目標パラメータ間の距離尺度(例えばメルケプストラムひずみ)が用いられる.しかしながら,同一話者が同一文を発話した際においても,スペクトルパラメータは変動するため,スペクトルパラメータ間の距離は零とはならない.また,特にリアルタイム変換処理においては,複雑な変換処理を韻律パ …

    IEICE technical report. Speech 112(281), 13-18, 2012-11-01

    References (11)

  • Brainwave Biometrics:A New Feature Extraction Approach with the Cepstral Analysis Method


    … Hence, we applied the cepstral analysis method, which is commonly used in speech recognition, for feature extraction for brainwave biometrics. … We tested the performance of our biometric system using the Mahalanobis distance as the threshold and estimated the equal error rate (EER) value to be 0.17. …

    Transactions of Japanese Society for Medical and Biological Engineering 50(1), 162-167, 2012


  • Music retrieval method based on filter-bank feature and earth mover's distance  [in Japanese]

    柘植 覚 , 三好 真人 , 肖 清梅 [他] , 北 研二

    … 本稿では,フィルタバンク特徴量と Earth Mover's Distance (EMD) を用いた音楽検索手法を提案する.提案手法では,音楽データから抽出される MFCC (melfrequency cepstral coefficient) をクラスタリングし求められた各クラスタのセントロイドおよび各クラスタに属する MFCC の個数を特徴量として使用する.音楽検索を行う際の距離尺度として用いた EMD は,2 つの離散分布において一方の分布を他方の分布に変換 …

    研究報告 音楽情報科学(MUS) 2011-MUS-89(22), 1-6, 2011-02-04


  • 21068 Localized Detection of Structural Damage Using Distance Measures of Low-order AR Models

    Xing Zhenhua , Mita Akira

    学術講演梗概集. B-2, 構造II, 振動, 原子力プラント (2010), 135-136, 2010-07-20


  • Cepstral Domain Feature Extraction Utilizing Entropic Distance-Based Filterbank

    SUH Youngjoo , KIM Hoirin

    … In this paper, we propose a new cepstral domain feature extraction approach utilizing the entropic distance-based filterbank for highly accurate speech recognition. … Experimental results showed that the cepstral features employing the proposed filterbank reduce the relative error by 31% for clean as well as noisy speech compared to the mel-cepstral features. …

    IEICE Transactions on Information and Systems 93(2), 392-394, 2010-02-01

    J-STAGE References (5)

  • Unsupervised Phoneme Segmentation Using Mahalanobis Distance

    QIAO Yu , MINEMATSU Nobuaki

    … An objective function, summation of squared error (SSE), is developed by using Euclidean distance of cepstral features. … However, it is not known whether or not Euclidean distance yields the best distance metric to estimate the goodness of segmentations. … A popular generalization of Euclidean distance is Mahalanobis distance (MD). …

    IEICE technical report 107(551), 69-74, 2008-03-13

    References (12)

  • Robust Speech Recognition by Combining Short-Term and Long-Term Spectrum Based Position-Dependent CMN with Conventional CMN

    WANG Longbiao , NAKAGAWA Seiichi , KITAOKA Norihide

    … Conventional short-term spectrum based Cepstral Mean Normalization (CMN) is therefore, not effective under these conditions. … We assume that a static speech segment (such as a vowel, for example) affected by reverberation, can be modeled by a long-term cepstral analysis. … The cepstral distance of neighboring frames is used to discriminate the static speech segment (long-term spectrum) and the non-static speech segment (short-term spectrum). …

    IEICE Transactions on Information and Systems 91(3), 457-466, 2008-03-01

    IR J-STAGE References (34) Cited by (2)

  • 21001 Damage Detection Using Distance between ARMA models

    Haitao Zheng , Akira Mita

    学術講演梗概集. B-2, 構造II, 振動, 原子力プラント (2007), 1-2, 2007-07-31


  • Factor analysis of dereverberated speech quality  [in Japanese]

    FURUYA Ken'ichi , KATAOKA Akitoshi

    本報告では,残響抑圧処理された音声の品質を,良く知られている9種の客観尺度と主観評価値MOSにより評価・分析を行った.因子分析で主観評価結果を分析することにより品質の決定要因を抽出し,それらの因子に対応する物理的な客観尺度を明らかにした.その結果,品質を決定する要因として,主に残響時間に対応する主観因子(残響感),STI(音声明瞭度指数)に対応する主観因子(明瞭性),SNRに対応する主観因子(自然 …

    IEICE technical report 107(120), 13-18, 2007-06-22

    References (22)

  • Predictive Trellis-Coded Quantization of the Cepstral Coefficients for the Distributed Speech Recognition

    KANG Sangwon , LEE Joonseok

    … In this paper, we propose a predictive block-constrained trellis-coded quantization (BC-TCQ) to quantize cepstral coefficients for distributed speech recognition. … For prediction of the cepstral coefficients, the first order auto-regressive (AR) predictor is used. … The quantization is compared to the split vector quantizers used in the ETSI standard, and is shown to lower cepstral distance and bit rates. …

    IEICE transactions on communications 90(6), 1570-1572, 2007-06-01

    References (7)

  • Idiosyncrasy of nasal sounds in human speaker identification and their acoustic properties

    AMINO Kanae , SUGAWARA Tsutomu , ARAI Takayuki

    Acoustical Science and Technology 27(4), 233-235, 2006-07-01

    J-STAGE NDL Digital Collections References (11) Cited by (3)

  • The Analysis of Acoustic and Linguistic Characteristics in Spontaneous Japanese  [in Japanese]

    NAKAMURA Masanobu , IWANO Koji , FURUI Sadaoki

    近年,新聞記事やニュース原稿などの読み上げ音声の認識においては高い認識率を得られるようになったが,話し言葉音声の認識を行うとその認識精度は極端に低下する.この間題に対し,話し言葉音声の認識性能の低下の原因を明らかにするため,日本語話し言葉コーパスをはじめとした複数の大規模コーパスを用いて話し言葉音声と読み上げ音声の音響的・言語的特徴の定量的・統計的な比較を行なった.分析の結果,話し言葉音声の認識性 …

    IEICE technical report 106(78), 19-24, 2006-05-19

    References (5) Cited by (3)

  • Driver Identification through Cepstrum Analysis of Driving Behavioral Signals  [in Japanese]

    OZAWA Koji , NISHIWAKI Yoshihiro , WAKITA Toshihiro , MIYAJIMA Chiyomi , ITOU Katsunobu , TAKEDA Kazuya

    … For example, the use of driver's characteristics of the way of controlling vehicle speed, keeping headway distance, and hitting the accelerator pedal will allow us to achieve driver recognition for automatic adaptation of vehicle environments. …

    IPSJ SIG Notes 2006(12(2006-SLP-060)), 19-24, 2006-02-03

    IPSJ References (12) Cited by (1)

  • A noise reduction system based on hybrid noise estimation technique and post-filtering in arbitrary noise environments

    Li Junfeng , Akagi Masato

    … Experimental results demonstrated that the hybrid estimation technique produces more accurate spectral estimates for localized noises and the proposed noise reduction system results in significant improvements in terms of objective speech quality measures: segmental SNR (SEGSNR) and Mel-Frequency Cepstral Coefficient (MFCC) distance and subjective speech quality measures: spectrograms and listening tests in various noise conditions. …

    Speech Communication 48(2), 111-126, 2006-02

    IR DOI Cited by (4)

  • Modeling of Individual Characteristics in Driving Signals  [in Japanese]

    OZAWA Koji , WAKITA Toshihiro , MIYAJIMA Chiyomi , ITOU Katsunobu , TAKEDA Kazuya

    速度, 車間距離, あるいはアクセル・ブレーキペダル操作信号といった走行観測信号を用いた運転行動のモデル化に関する研究が盛んに行われている.運転行動はドライバによって異なり, 認知科学や工学的な観点から, 様々なドライバモデルに関する研究が行われている.本研究では, ドライバの運転行動をソースフィルタモデルと仮定し, アクセルペダル踏力信号をケプストラム分析することによって, ドライバがペダルを踏 …

    IEICE technical report. Speech 105(297), 59-64, 2005-09-17

  • Modeling of Individual Characteristics in Driving Signals  [in Japanese]

    OZAWA Koji , WAKITA Toshihiro , MIYAJIMA Chiyomi , ITOU Katsunobu , TAKEDA Kazuya

    速度, 車間距離, あるいはアクセル・ブレーキペダル操作信号といった走行観測信号を用いた運転行動のモデル化に関する研究が盛んに行われている.運転行動はドライバによって異なり, 認知科学や工学的な観点から, 様々なドライバモデルに関する研究が行われている.本研究では, ドライバの運転行動をソースフィルタモデルと仮定し, アクセルペダル踏力信号をケプストラム分析することによって, ドライバがペダルを踏 …

    IEICE technical report. Signal processing 105(293), 59-64, 2005-09-17

    Cited by (2)

  • 1 / 2
Page Top