Utterance-Based Selective Training for the Automatic Creation of Task-Dependent Acoustic Models(Speech Recognition, <Special Section> Statistical Modeling for Speech Processing)
スポンサーリンク
概要
- 論文の詳細を見る
To obtain a robust acoustic model for a certain speech recognition task, a large amount of speech data is necessary. However, the preparation of speech data including recording and transcription is very costly and time-consuming. Although there are attempts to build generic acoustic models which are portable among different applications, speech recognition performance is typically task-dependent. This paper introduces a method for automatically building task-dependent acoustic models based on selective training. Instead of setting up a new database, only a small amount of task-specific development data needs to be collected. Based on the likelihood of the target model parameters given this development data, utterances which are acoustically close to the development data are selected from existing speech data resources. Since there are too many possibilities for selecting a data subset from a larger database in general, a heuristic has to be employed. The proposed algorithm deletes single utterances temporarily or alternates between successive deletion and addition of multiple utterances. In order to make selective training computationally practical, model retraining and likelihood calculation need to be fast. It is shown, that the model likelihood can be calculated fast and easily based on sufficient statistics without the need for explicit reconstruction of model parameters. The algorithm is applied to obtain an infant- and elderly-dependent acoustic model with only very few development data available. There is an improvement in word accuracy of up to 9% in comparison to conventional EM training without selection. Furthermore, the approach was also better than MLLR and MAP adaptation with the development data.
- 社団法人電子情報通信学会の論文
- 2006-03-01
著者
-
TODA Tomoki
Graduate School of Information Science, Nara Institute of Science and Technology
-
Toda Tomoki
Nara Institute Of Science And Technology
-
Toda Tomoki
The Graduate School Of Information Science Nara Institute Of Science And Technology
-
SARUWATARI Hiroshi
Nara Institute of Science and Technology
-
SHIKANO Kiyohiro
Nara Institute of Science and Technology
-
CINCAREK Tobias
Graduate School of Information Science, Nara Institute of Science and Technology
-
CINCAREK Tobias
the Graduate School of Information Science, Nara Institute of Science and Technology
-
SARUWATARI Hiroshi
the Graduate School of Information Science, Nara Institute of Science and Technology
-
SHIKANO Kiyohiro
the Graduate School of Information Science, Nara Institute of Science and Technology
-
Cincarek Tobias
Graduate School Of Information Science Nara Institute Of Science And Technology
-
Shikano K
Chiba University And National Institute Of Information And Communications Technology
-
Sawada H
Graduate School Of Information Science Nara Institute Of Science And Technology
関連論文
- The Nitech-NAIST HMM-Based Speech Synthesis System for the Blizzard Challenge 2006
- Details of the Nitech HMM-Based Speech Synthesis System for the Blizzard Challenge 2005(Speech and Herring)
- Development of real-time audio localization control system (応用音響)
- EA2010-24 Development of real-time audio localization control system
- A Speech Parameter Generation Algorithm Considering Global Variance for HMM-Based Speech Synthesis(Speech and Hearing)
- Sound reproduction based on multi-channel inverse filtering and WFS
- The Nitech-NAIST HMM-Based Speech Synthesis System for the Blizzard Challenge 2006
- Building an Effective Speech Corpus by Utilizing Statistical Multidimensional Scaling Method
- Cost Reduction of Acoustic Modeling for Real-Environment Applications Using Unsupervised and Selective Training
- Reducing Computation Time of the Rapid Unsupervised Speaker Adaptation Based on HMM-Sufficient Statistics(Speech and Hearing)
- Improving Rapid Unsupervised Speaker Adaptation Based on HMM-Sufficient Statistics in Noisy Environments Using Multi-Template Models(Speech Recognition, Statistical Modeling for Speech Processing)
- Utterance-Based Selective Training for the Automatic Creation of Task-Dependent Acoustic Models(Speech Recognition, Statistical Modeling for Speech Processing)
- Designing Target Cost Function Based on Prosody of Speech Database(Speech Synthesis and Prosody, Corpus-Based Speech Technologies)
- Designing Target Cost Function Based on Prosody of Speech Database
- Cross-language Voice Conversion Evaluation Using Bilingual Databases (特集 音声言語情報処理とその応用)
- A MAP Estimator for the Enhancement of Speech Signal Separated by ICA Algorithm (国際ワークショップ Frontiers in Speech and Hearing Research)
- Effect of Central Limit Theorem non-compliance on blind separation of speech by negentropy maximization
- Blind Separation of Speech by Fixed-Point ICA with Source Adaptive Negentropy Approximation(Blind Source Separation, Multi-channel Acoustic Signal Processing)
- Robots that can hear, understand and talk
- Probability Distribution of Time-Series of Speech Spectral Components(Audio/Speech Coding)(Applications and Implementations of Digital Signal Processing)
- 音声情報案内システム「たけまるくん」および「キタちゃん」の開発(特別企画「音声認識デベロッパーズフォーラム」)
- A Microphone Array-Based 3-D N-Best Search Method for Recognizing Multiple Sound Sources
- 3D N-best 探索法に基づく複数音源の位置推定と音声認識の統合
- 複数話者の音声認識における音源方向経路間距離を用いた3-D N-best探索法の評価
- Non-Audible Murmur (NAM) Recognition Exploiting Adaptation Techniques
- An HMM State Duration Control Algorithm Applied to Large-Vocabulary Spontaneous Speech Recognition
- Development and evaluation of pocket-size real-time blind source separation microphone
- Objective sound quality comparison based on higher-order statistics for nonlinear noise reduction methods (応用音響)
- Objective sound quality evaluation for combination method of beamforming and spectral subtraction (応用音響)
- Fast Convergence Blind Source Separation Using Frequency Subband Interpolation by Null Beamforming
- Rapid Compensation of Temperature Fluctuation Effect for Multichannel Sound Field Reproduction System
- Development, Long-Term Operation and Portability of a Real-Environment Speech-Oriented Guidance System
- Interface for Barge-in Free Spoken Dialogue System Using Nullspace Based Sound Field Control and Beam forming (Speech/Audio Processing, Multidimensional Signal Processing and Its Application)
- On-Line Relaxation Algorithm Applicable to Acoustic Fluctuation for Inverse Filter in Multichannel Sound Reproduction System(Sound Field Reproduction, Multi-channel Acoustic Signal Processing)
- 複数モデルを用いた十分統計量に基く教師なし話者適応における学習話者のクラス化の検討
- Iterative Inverse Filter Relaxation Algorithm for Adaptation to Acoustic Fluctuation in Sound Reproduction System
- Sound Reproduction System Including Adaptive Compensation of Temperature Fluctuation Effect for Broad-Band Sound Control(Special Section on Digital Signal Processing)
- Maximum Likelihood Successive State Splitting Algorithm for Tied-Mixture HMnet
- A Self-Generator Method for Initial Filters of SIMO-ICA Applied to Blind Separation of Binaural Sound Mixtures(Blind Source Separation, Multi-channel Acoustic Signal Processing)
- Multistage SIMO-Model-Based Blind Source Separation Combining Frequency-Domain ICA and Time-Domain ICA(Adaptive Signal Processing and Its Applications)
- Evaluation of Extremely Small Sound Source Signals Used in Speaking-Aid System with Statistical Voice Conversion
- Improvements of the One-to-Many Eigenvoice Conversion System
- Esophageal Speech Enhancement Based on Statistical Voice Conversion with Gaussian Mixture Models
- Adaptive Training for Voice Conversion Based on Eigenvoices
- Blind Separation and Deconvolution for Convolutive Mixture of Speech Combining SIMO-Model-Based ICA and Multichannel Inverse Filtering(Engineering Acoustics)
- High-Fidelity Blind Separation of Acoustic Signals Using SIMO-Model-Based Independent Component Analysis(Engineering Acoustics)
- A Speech Dialogue System with Multimodal Interface for Telephone Directory Assistance
- Overdetermined Blind Separation for Real Convolutive Mixtures of Speech Based on Multistage ICA Using Subarray Processing(Speech/Acoustic Signal Processing)(Digital Signal Processing)
- Stable Learning Algorithm for Blind Separation of Temporally Correlated Acoustic Signals Combining Multistage ICA and Linear Prediction(Digital Signal Processing)
- Blind Source Separation of Acoustic Signals Based on Multistage ICA Combining Frequency-Domain ICA and Time-Domain ICA
- Fast-Convergence Algorithm for Blind Source Separation Based on Array Signal Processing
- An Iterative Inverse Filter Design Method for the Multichannel Sound Field Sound Field Reproduction System(Special Section on Acoustic Signal Processing)
- Sound Field Reproduction by Wavefront Synthesis Using Directly Aligned Multi Point Control
- Theoretical Analysis of Amounts of Musical Noise and Speech Distortion in Structure-Generalized Parametric Blind Spatial Subtraction Array
- Speech Prior Estimation for Generalized Minimum Mean-Square Error Short-Time Spectral Amplitude Estimator
- Comparison of Methods for Topic Classification of Spoken Inquiries
- Robust Sound Field Reproduction against Listeners Movement Utilizing Image Sensor