Dimensional feature weighting utilizing multiple kernel learning for single-channel talker location discrimination using the acoustic transfer function
-
- Ryoichi Takashima
- Kobe University Graduate School of System Informatics, , 1-1 Rokkodai, Nada-ku, Kobe, 657-8501 Japan
-
- Tetsuya Takiguchi
- Kobe University Organization of Advanced Science and Technology, , 1-1 Rokkodai, Nada-ku, Kobe, 657-8501 Japan
-
- Yasuo Ariki
- Kobe University Organization of Advanced Science and Technology, , 1-1 Rokkodai, Nada-ku, Kobe, 657-8501 Japan
書誌事項
- 公開日
- 2013-01-30
- 資源種別
- journal article
- DOI
-
- 10.1121/1.4773255
- 公開者
- Acoustical Society of America (ASA)
この論文をさがす
説明
<jats:p>This paper presents a method for discriminating the location of the sound source (talker) using only a single microphone. In a previous work, the single-channel approach for discriminating the location of the sound source was discussed, where the acoustic transfer function from a user's position is estimated by using a hidden Markov model of clean speech in the cepstral domain. In this paper, each cepstral dimension of the acoustic transfer function is newly weighted, in order to obtain the cepstral dimensions having information that is useful for classifying the user's position. Then, this paper proposes a feature-weighting method for the cepstral parameter using multiple kernel learning, defining the base kernels for each cepstral dimension of the acoustic transfer function. The user's position is trained and classified by support vector machine. The effectiveness of this method has been confirmed by sound source (talker) localization experiments performed in different room environments.</jats:p>
収録刊行物
-
- The Journal of the Acoustical Society of America
-
The Journal of the Acoustical Society of America 133 (2), 891-901, 2013-01-30
Acoustical Society of America (ASA)
