Unsupervised Training with Directed Manual Transcription for Recognising Mandarin
نویسندگان
چکیده
The performance of unsupervised discriminative training has been found to be highly dependent on the accuracy of the initial automatic transcription. This paper examines a strategy where a relatively small amount of poorly recognised data are manually transcribed to supplement the automatically transcribed data. Experiments were carried out on a Mandarin broadcast transcription task using both Broadcast News (BN) and Broadcast Conversation (BC) data. A range of experimental conditions are compared for both maximum likelihood and discriminative training using directed manual transcription. For BC data, using fully unsupervised discriminative training, only 17% of the reduction in character error rate (CER) from supervised training is obtained. By automatically selecting 18% of the data for manual transcription yields 50% of the CER gain from supervised training. The directed approach to selecting data outperforms the use of a random set of data for manual transcription.
منابع مشابه
Unsupervised training with directed manual transcription for recognising Mandarin broadcast audio
The performance of unsupervised discriminative training has been found to be highly dependent on the accuracy of the initial automatic transcription. This paper examines a strategy where a relatively small amount of poorly recognised data are manually transcribed to supplement the automatically transcribed data. Experiments were carried out on a Mandarin broadcast transcription task using both ...
متن کاملUnsupervised training and directed manual transcription for LVCSR
A significant cost in obtaining acoustic training data is the generation of accurate transcriptions. When no transcription is available, unsupervised training techniques must be used. Furthermore, the use of discriminative training has become a standard feature of state-ofthe-art large vocabulary continuous speech recognition (LVCSR) system. In unsupervised training, unlabelled data are recogni...
متن کاملThe CMU-interACT 2008 Mandarin transcription system
We present our Mandarin BN/BC transcription system recently developed for the GALE07 evaluation. The system employs a 3-pass decoding strategy trained with over 1300 hours of quickly transcribed audio. We successfully apply discriminative training, dynamic unsupervised language model adaptation, and system combination techniques in our system. We furthermore achieve improvements by combining an...
متن کاملDynamic language modeling for broadcast news
This paper describes some recent experiments on unsupervised language model adaptation for transcription of broadcast news data. In previous work, a framework for automatically selecting adaptation data using information retrieval techniques was proposed. This work extends the method and presents experimental results with unsupervised language model adaptation. Three primary aspects are conside...
متن کاملEffective Utterance Classification with Unsupervised Phonotactic Models
This paper describes a method for utterance classification that does not require manual transcription of training data. The method combines domain independent acoustic models with off-the-shelf classifiers to give utterance classification performance that is surprisingly close to what can be achieved using conventional word-trigram recognition requiring manual transcription. In our method, unsu...
متن کامل