Integrating MAP, marginals, and unsupervised language model adaptation
Explore this paper's citation graph
Summary
It is found that by effectively combining these adaptation approaches, one can achieve as much as 1.3% absolute gain on the final recognition error rate in the BC genre.
- Type
- article
- Published
- 2007-08-27
- Cited by
- 14
- References
- 10
- OpenAlex
- https://openalex.org/W79427365
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:11135734
Keywords
Adaptation (eye), Computer science, Mandarin Chinese, Conversation, Language model
References
- Unsupervised language model adaptation for Mandarin broadcast conversation transcription
- Language model adaptation using dynamic marginals
- The 1998 HTK broadcast news transcription system: development and results
- An efficient repair procedure for quick transcriptions
- Investigation on Mandarin broadcast news speech recognition
- Statistical language model adaptation: review and perspectives
- Combining Discriminative Feature, Transform, and Model Training for Large Vocabulary Speech Recognition
- Web-data augmented language models for Mandarin conversational speech recognition
- Unsupervised language model adaptation
- The AT&T LVCSR-2000 System
Cited by
- Informations morpho-syntaxiques et adaptation thématique pour améliorer la reconnaissance de la parole
- Bag-of-word normalized n-gram models
- Multifactor adaptation for Mandarin broadcast news and conversation speech recognition
- Estimating Confusions in the ASR Channel for Improved Topic-based Language Model Adaptation
- Unsupervised language model adaptation for handwritten Chinese text recognition
- Dynamic language modeling for European Portuguese
- Language Model Adaptation for Relevance Feedback in Information Retrieval
- Contributions to speech analytics based on speech recognition and topic identification
- Filtering web text to match target genres
- Improving unsupervised language model adaptation with discriminative data filtering
- Automatic Annotation of Spoken Language Using Out-of-Domain Resources and Domain Adaptation
- A dynamic term discovery strategy for automatic speech recognizers with evolving dictionaries
- Contributions to speech analytics based on speech recognition and topic identification
- Language Model Adaptation for Relevance Feedback in Information Retrieval
- of Domain Adaptation with Unlabeled Data
- A Literature Review of Domain Adaptation with Unlabeled Data
Related papers
- A preliminary exploration on tone error detection in Mandarin based on clustering
- An empirical study of statistical language models: n-gram language models vs. neural network language models
- Language Model Adaptation for Statistical Machine Translation Based on Information Retrieval
- Code-Switch Language Model with Inversion Constraints for Mixed Language Speech Recognition
- Trends and challenges in language modeling for speech recognition and machine translation
- Incorporating language constraints in sub-word based speech recognition
- Muscular dystrophy with separate clinical phenotypes in a large family
- Automatic transcription of lecture speech using topic-independent language modeling
- Evaluating Modeling Units and Sub-word Features in Language Models for Turkish ASR