Risk-Based Semi-Supervised Discriminative Language Modeling for Broadcast Transcription
スポンサーリンク
概要
- 論文の詳細を見る
This paper describes a new method for semi-supervised discriminative language modeling, which is designed to improve the robustness of a discriminative language model (LM) obtained from manually transcribed (labeled) data. The discriminative LM is implemented as a log-linear model, which employs a set of linguistic features derived from word or phoneme sequences. The proposed semi-supervised discriminative modeling is formulated as a multi-objective optimization programming problem (MOP), which consists of two objective functions defined on both labeled lattices and automatic speech recognition (ASR) lattices as unlabeled data. The objectives are coherently designed based on the expected risks that reflect information about word errors for the training data. The model is trained in a discriminative manner and acquired as a solution to the MOP problem. In transcribing Japanese broadcast programs, the proposed method reduced relatively a word error rate by 6.3% compared with that achieved by a conventional trigram LM.
- The Institute of Electronics, Information and Communication Engineersの論文
著者
-
Nakagawa Seiichi
Toyohashi Univ. Of Technol. Toyohashi‐shi Jpn
-
Imai Toru
Nhk Science And Technical Research Laboratories
-
KOBAYASHI Akio
NHK Science and Technical Research Laboratories
-
IMAI Toru
NHK Science and Technology Research Laboratories
-
OKU Takahiro
NHK Science and Technology Research Laboratories
関連論文
- Auditory perception versus automatic estimation of location and orientation of an acoustic source in a real environment
- TEXT-INDEPENDENT SPEAKER IDENTIFICATION ON TIMIT DATABASE
- Robust Speech Recognition by Using Compensated Acoustic Scores(Speech Recognition, Statistical Modeling for Speech Processing)
- Mutual Information Based Dynamic Integration of Multiple Feature Streams for Robust Real-Time LVCSR
- Bi-Spectral Acoustic Features for Robust Speech Recognition
- Online Speech Detection and Dual-Gender Speech Recognition for Captioning Broadcast News(Speech and Hearing)
- Word Error Rate Minimization Using an Integrated Confidence Measure(Speech and Hearing)
- Filter Bank Subtraction for Robust Speech Recognition (Special Issue on Speech Information Processing)
- Simultaneous Subtitling System for Broadcast News Programs with a Speech Recognizer(Special Issue on the 2001 IEICE Excellent Paper Award)
- Acoustic Model Adaptation by Selective Training Using 2-Stage Clustering
- An HMM learning algorithm for minimizing an error function on all training data
- Evaluation of Combinational Use of Discriminant Analysis-Based Acoustic Feature Transformation and Discriminative Training
- Linear Discriminant Analysis Using a Generalized Mean of Class Covariances and Its Application to Speech Recognition
- Robust Speech Recognition by Combining Short-Term and Long-Term Spectrum Based Position-Dependent CMN with Conventional CMN
- Noisy Speech Recognition Based on Integration/Selection of Multiple Noise Suppression Methods Using Noise GMMs
- A Survey on Automatic Speech Recognition(Special Issue on the 2000 IEICE Excellent Paper Award)
- Speaker Recognition by Combining MFCC and Phase Information in Noisy Conditions
- Learning Speech Variability in Discriminative Acoustic Model Adaptation
- Distant-Talking Speech Recognition Based on Spectral Subtraction by Multi-Channel LMS Algorithm
- Response Timing Detection Using Prosodic and Linguistic Information for Human-friendly Spoken Dialog Systems
- 連続発話認識のための言語モデル
- INVESTIGATIONS ON TEXT-INDEPENDENT SPEAKER IDENTIFICATION
- Risk-Based Semi-Supervised Discriminative Language Modeling for Broadcast Transcription
- Decoder for Japanese broadcast news transcription
- Risk-Based Semi-Supervised Discriminative Language Modeling for Broadcast Transcription