scispace - formally typeset
PatentDOI

Recognition unit model training based on competing word and word string models

Wu Chou, +1 more
- 15 Mar 1993 - 
- Vol. 102, Iss: 3, pp 1284
TLDR
The principle of minimum recognition error rate is applied by the present invention using discriminative training and various issues related to the special structure of HMMs are presented.
Abstract
A system pattern-based speech recognition, e.g., a hidden Markov model (HMM) based speech recognizer using Viterbi scoring. The principle of minimum recognition error rate is applied by the present invention using discriminative training. Various issues related to the special structure of HMMs are presented. Parameter update expressions for HMMs are provided.

read more

Citations
More filters
Patent

Intelligent Automated Assistant

TL;DR: In this article, an intelligent automated assistant system engages with the user in an integrated, conversational manner using natural language dialog, and invokes external services when appropriate to obtain information or perform various actions.
Patent

Automated Response to and Sensing of User Activity in Portable Devices

TL;DR: In this paper, various methods and devices described herein relate to devices which, in at least certain embodiments, may include one or more sensors for providing data relating to user activity and at least one processor for causing the device to respond based on the user activity which was determined, at least in part, through the sensors.
Patent

Using context information to facilitate processing of commands in a virtual assistant

TL;DR: In this article, a virtual assistant uses context information to supplement natural language or gestural input from a user, which helps to clarify the user's intent and reduce the number of candidate interpretations of user's input, and reduces the need for the user to provide excessive clarification input.
Patent

Method and apparatus for building an intelligent automated assistant

TL;DR: In this paper, a method for building an automated assistant includes interfacing a service-oriented architecture that includes a plurality of remote services to an active ontology, where the active ontologies includes at least one active processing element that models a domain.
Patent

Contextual voice commands

TL;DR: In this paper, techniques and systems for implementing contextual voice commands are described and a physical input that relates the selected data item to an operation in a second context is received, and the operation is performed on the input data item in the second context.
References
More filters
PatentDOI

Speech recognition system having word-based and phoneme-based recognition means

TL;DR: A speech recognition system includes a parameter extracting section for extracting a speech parameter of input speech, a first recognizing section for performing recognition processing by word-based matching, and a second recognizing sectionfor performing word recognition by matching in units of word constituent elements.
PatentDOI

Rapidly training a speech recognizer to a subsequent speaker given training data of a reference speaker

TL;DR: In this article, label output probabilities for subsequent speakers are re-parameterized based on confusion matrix entries having values indicative of the similarity between an lth label output of the subsequent speaker and a kth output for the reference speaker.
PatentDOI

Method of optimizing a composite speech recognition expert

TL;DR: In this article, a method for adjusting the relative weighting to be applied to those scores employing training data utilizing the words to be recognized in multiple word phrases is disclosed, where multiple word test phrases are applied to the acoustic expert to determine, for each phrase, plural multi-word hypotheses each having corresponding cumulative scores.
Related Papers (5)