Neural-network-based HMM adaptation for noisy speech recognition
スポンサーリンク
概要
- 論文の詳細を見る
This paper proposes a new method, using neural networks, of adapting phone HMMs to noisy speech. The neural networks are designed to map clean speech HMMs to noise-adapted HMMs, using noise HMMs and signal-to-noise ratios (SNRs) as inputs. The neural network is trained by minimizing the mean square error between the output HMMs and the target noise-adapted HMMs, In an evaluation, the proposed method was used to recognize noisy broadcast-news speech in speaker-dependent and speaker-independent modes. The trained networks were found to be effective in recognizing new speakers under new noise and various SNR conditions.
- 社団法人日本音響学会の論文
著者
-
ITOH Daisuke
Department of Bio-organic Science, Obihiro University of Agriculture and Veterinary Medicine
-
Furui S
Tokyo Inst. Technol. Tokyo Jpn
-
Furui Sadaoki
Department Of Computer Science Graduate School Of Information Science And Engineering Tokyo Institut
-
Itoh Daisuke
Department Of Computer Science Tokyo Institute Of Technology
-
Zhang Zhipeng
Department Of Computer Science Tokyo Institute Of Technology
関連論文
- Gait-based Person Identification Robust against Speed Variation using CHLAC features and HMMs
- Gait-based Person Identification Robust against Speed Variation using CHLAC features and HMMs
- Gait-based Person Identification Robust against Speed Variation using CHLAC features and HMMs
- Tree-Structured Clustering Methods for Piecewise Linear-Transformation-Based Noise Adaptation(Speech and Hearing)
- Labeling Patterns of Chloroplastidic Isoprenoids in Cultured Cells of Liverwort Ptychanthus striatus
- Robust Scene Extraction Using Multi-Stream HMMs for Baseball Broadcast(Image Processing and Video Processing)
- Automatic recognition of Indonesian declarative questions and statements using polynomial coefficients of the pitch contours
- Initial evaluation of the drivers' Japanese speech corpus in a car environment (Speech) -- (国際ワークショップ"Asian workshop on speech science and technology")
- Accent analysis for Mandarin large vocabulary continuous speech recognition (Speech) -- (国際ワークショップ"Asian workshop on speech science and technology")
- Evaluation of a Noise-Robust Multi-Stream Speaker Verification Method Using F_0 Information