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. The system can be implemented using any of a number of different platforms, such as the web, email, smartphone, and the like, or any combination thereof. In one embodiment, the system is based on sets of interrelated domains and tasks, and employs additional functionally powered by external services with which the system can interact.

Intelligent Automated Assistant

This chapter introduces the subject of statistical pattern recognition (SPR). It starts by considering how features are defined and emphasizes that the nearest neighbor algorithm achieves error rates comparable with those of an ideal Bayes’ classifier. The concepts of an optimal number of features, representativeness of the training data, and the need to avoid overfitting to the training data are stressed. The chapter shows that methods such as the support vector machine and artificial neural networks are subject to these same training limitations, although each has its advantages. For neural networks, the multilayer perceptron architecture and back-propagation algorithm are described. The chapter distinguishes between supervised and unsupervised learning, demonstrating the advantages of the latter and showing how methods such as clustering and principal components analysis fit into the SPR framework. The chapter also defines the receiver operating characteristic, which allows an optimum balance between false positives and false negatives to be achieved.

Statistical Pattern Recognition

Systems, methods, and computer program products for machine translation are provided. In some implementations a system is provided. The system includes a language model including a collection of n-grams from a corpus, each n-gram having a corresponding relative frequency in the corpus and an order n corresponding to a number of tokens in the n-gram, each n-gram corresponding to a backoff n-gram having an order of n-1 and a collection of backoff scores, each backoff score associated with an n-gram, the backoff score determined as a function of a backoff factor and a relative frequency of a corresponding backoff n-gram in the corpus.

/pdf/large-language-models-in-machine-translation-3wqubjuzrp.pdf

Large Language Models in Machine Translation

A virtual assistant uses context information to supplement natural language or gestural input from a user. Context helps to clarify the user's intent and to reduce the number of candidate interpretations of the user's input, and reduces the need for the user to provide excessive clarification input. Context can include any available information that is usable by the assistant to supplement explicit user input to constrain an information-processing problem and/or to personalize results. Context can be used to constrain solutions during various phases of processing, including, for example, speech recognition, natural language processing, task flow processing, and dialog generation.

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

A method and apparatus are provided for building an intelligent automated assistant. Embodiments of the present invention rely on the concept of “active ontologies” (e.g., execution environments constructed in an ontology-like manner) to build and run applications for use by intelligent automated assistants. In one specific embodiment, 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 ontology includes at least one active processing element that models a domain. At least one of the remote services is then registered for use in the domain.

Method and apparatus for building an intelligent automated assistant

An apparatus for providing dynamic vocabulary prediction for setting up a speech recognition network of resource constrained portable devices may include a recognition network element. The recognition network element may be configured to determine a confidence measure for each candidate recognized word for a current word to be recognized. The recognition network element may also be configured to select a subset of candidate recognized words as selected candidate words based on the confidence measure of each one of the candidate recognized words, and determine a recognition network for a next word to be recognized, the recognition network including likely follower words for each of the selected candidate words, e.g. using language model and highly frequently used words.

System, Method, Apparatus and Computer Program Product for Providing Dynamic Vocabulary Prediction for Speech Recognition

Words in a sequence of words that is obtained from speech recognition of an input speech sequence are presented to a user, and at least one of the words in the sequence of words is replaced, in case it has been selected by a user for correction. Words with a low recognition confidence value are emphasized; alternative word candidates for the at least one selected word are ordered according to an ordering criterion; after replacing a word, an order of alternative word candidates for neighboring words in the sequence is updated; the replacement word is derived from a spoken representation of the at least one selected word by speech recognition with a limited vocabulary; and the word that replaces the at least one selected word is derived from a spoken and spelled representation of the at least one selected word.

Error correction for speech recognition systems

A method, devices, computer program products and an internet service is disclosed for adapting a context model. In the method a media clip is received. Also sensor data captured at least partly when the media clip was captured is received. A context is derived using a context model based at least partly on the sensor data and an indication on the context is provided to a user. Feedback on the relevance of the context is received from the user. Based on the feedback, the context model may then be adapted.

Method and apparatus for adapting a context model

Apparatus for audio processing comprises: a beat tracking module for identifying beat time instants in an audio signal and a downbeat identifier for identifying downbeats occurring at beat time instants, each downbeat corresponding to the start of a musical bar or measure. A pattern identifier identifies two or more adjacent bars or measures containing musical characteristics which repeat within the audio signal, the pattern identifier being configured to: generate for each downbeat a plurality of scores using respective analysis methods for indicating different characteristics within the audio signal at the downbeat; combine the scores for each downbeat; and identify based on the combined scores non-adjacent downbeats that correspond to the start of a musical pattern.

Audio signal analysis

There is disclosed a method including receiving sensor data extracted from one or more physical sensors, using the extracted sensor data and a context model to perform a first level context determination, and examining the at least one condition. If the examining indicated that the at least one condition was fulfilled, the context model is adapted on the basis of the sensor data, otherwise adaptation data formed on the basis of the sensor data is provided to a second level context determination. A corresponding apparatus and computer program product are also provided.

Jussi Leppänen

Papers

System, Method, Apparatus and Computer Program Product for Providing Dynamic Vocabulary Prediction for Speech Recognition

Error correction for speech recognition systems

Method and apparatus for adapting a context model

Audio signal analysis

Adaptation of context models