Journal ArticleDOI
Variable-length sequence modeling: multigrams
TLDR
A model that represents sentences as a concatenation of variable-length sequences of units and an algorithm for unsupervised estimation of the model parameters is presented and an approach is illustrated for the segmentation of sequences of letters into subword-like units.Abstract:
The conventional n-gram language model exploits dependencies between words and their fixed-length past. This letter presents a model that represents sentences as a concatenation of variable-length sequences of units and describes an algorithm for unsupervised estimation of the model parameters. The approach is illustrated for the segmentation of sequences of letters into subword-like units. It is evaluated as a language model on a corpus of transcribed spoken sentences. Multigrams can provide a significantly lower test set perplexity than n-gram models. >read more
Citations
More filters
Patent
Disambiguating user intent in conversational interaction system for large corpus information retrieval
Murali Aravamudan,Rakesh Barve,Sashikumar Venkataraman,Vineet Agarwal,Abhijit Satchidanand Savarkar,Ganesh Ramamoorthy,Ahmed Nizam Mohaideen Pathurudeen,K China Srinivasulu Reddy +7 more
TL;DR: In this paper, a method of disambiguating user intent in conversational interactions for information retrieval is presented, which includes access to a set of content items with metadata describing the content items and providing access to structural knowledge showing semantic relationships and links among the contents.
Journal ArticleDOI
Inference of variable-length linguistic and acoustic units by multigrams
Sabine Deligne,Frédéric Bimbot +1 more
TL;DR: A general formulation of the multigram model, applicable to single or multiple parallel strings of data having either discrete or continuous values, and used to infer a set of variable-length acoustic units, directly from speech data.
Patent
Method of and system for inferring user intent in search input in a conversational interaction system
TL;DR: In this article, a method of inferring user intent in search input in a conversational interaction system is disclosed, which includes providing a user preference signature that describes preferences of the user, and determining that a portion of the search input contains an ambiguous identifier.
Patent
Method of and system for using conversation state information in a conversational interaction system
TL;DR: In this paper, a method for inferring a change of a conversation session during continuous user interaction with an interactive content providing system includes receiving input from the user including linguistic elements intended by the user to identify an item, associating a linguistic element of the input with a first conversation session, and providing a response based on the input.
Proceedings ArticleDOI
Segmental vocoder-going beyond the phonetic approach
TL;DR: The problem of very low bit rate segmental speech coding is addressed and future extensions of the scheme (diphone-like synthesis and speaker adaptation) as well as possible use of automatically derived units in recognition are discussed.
References
More filters
Proceedings ArticleDOI
Multi-site data collection for a spoken language corpus
TL;DR: A recently collected spoken language corpus for the ATIS (Air Travel Information System) domain is described and the motivation for this effort, the goals, the implementation of a multi-site data collection paradigm, and the accomplishments of MADCOW are summarized.