Class phrase models for language modeling
Explore this paper's citation graph
- Type
- article
- Published
- 1996-10-03
- Cited by
- 55
- References
- 15
- Access
- Open access
- OpenAlex
- https://openalex.org/W2041167939
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:14309682
Keywords
Bigram, Perplexity, Trigram, Computer science, Language model
References
- Improved clustering techniques for class-based statistical language modelling
- Empirical acquisition of language models for speech recognition
- Towards better language models for spontaneous speech
- Language modeling by variable length sequences: theoretical formulation and evaluation of multigrams
- Improved backing-off for M-gram language modeling
- On automated language acquisition
- Improved language modelling by unsupervised acquisition of structure
- IMPROVED LANGUAGE MODELING BY UNSUPERVISED ACQUISITION OF STRUCTURE
- Part-of-Speech Tagging and Partial Parsing
Cited by
- Informations morpho-syntaxiques et adaptation thématique pour améliorer la reconnaissance de la parole
- Multimodal interactive error recovery for non-conversational speech user interfaces
- A language model combining n-grams and stochastic finite state automata
- Evaluating hierarchical hybrid statistical language models
- Beyond the conventional statistical language models: the variable-length sequences approach
- Hierarchical statistical language models: experiments on in-domain adaptation
- What makes a word: Learning base units in Japanese for speech recognition
- Phrases in category-based language models for Spanish and basque ASR
- Phrase-based language models for speech recognition
- Language-Model Investigations related to Broadcast News
- Bi-directional conversion between graphemes and phonemes using a joint N-gram model
- Performance of LVCSR with morpheme-based and syllable-based recognition units
- Utilisation de la linguistique en reconnaissance de la parole : un état de l'art
- Particle-based language modelling
- On transcribing informally-pronounced numbers in Romanian speech
- Statistical language modeling based on variable-length sequences
- Phrase classes in two-level language models for ASR
- Toward a unified approach to lexicon optimization and perplexity minimization for Chinese language modeling
- Two Approaches to Class-Based Language Models for ASR
- Data-driven approach to designing compound words for continuous speech recognition
Related papers
- Scalable backoff language models
- Improving language models by using distant information
- Evaluation of a language model using a clustered model backoff
- Factored Language Models and Generalized Parallel Backoff
- Decoupling Word-Pair Distance and Co-occurrence Information for Effective Long History Context Language Modeling
- First steps towards statistical modeling of dialogue to predict the speech act type of the next utterance
- Cleaning statistical language models