We propose a novel context-dependent (CD) model for large-vocabulary speech recognition (LVSR) that leverages recent advances in using deep belief networks for phone recognition. We describe a pre-trained deep neural network hidden Markov model (DNN-HMM) hybrid architecture that trains the DNN to produce a distribution over senones (tied triphone states) as its output. The deep belief network pre-training algorithm is a robust and often helpful way to initialize deep neural networks generatively that can aid in optimization and reduce generalization error. We illustrate the key components of our model, describe the procedure for applying CD-DNN-HMMs to LVSR, and analyze the effects of various modeling choices on performance. Experiments on a challenging business search dataset demonstrate that CD-DNN-HMMs can significantly outperform the conventional context-dependent Gaussian mixture model (GMM)-HMMs, with an absolute sentence accuracy improvement of 5.8% and 9.2% (or relative error reduction of 16.0% and 23.2%) over the CD-GMM-HMMs trained using the minimum phone error rate (MPE) and maximum-likelihood (ML) criteria, respectively.

/pdf/context-dependent-pre-trained-deep-neural-networks-for-large-14o17jhkzd.pdf

Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition

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

Recently, researchers have made significant progress combining the advances in deep learning for learning feature representations with reinforcement learning. Some notable examples include training agents to play Atari games based on raw pixel data and to acquire advanced manipulation skills using raw sensory inputs. However, it has been difficult to quantify progress in the domain of continuous control due to the lack of a commonly adopted benchmark. In this work, we present a benchmark suite of continuous control tasks, including classic tasks like cart-pole swing-up, tasks with very high state and action dimensionality such as 3D humanoid locomotion, tasks with partial observations, and tasks with hierarchical structure. We report novel findings based on the systematic evaluation of a range of implemented reinforcement learning algorithms. Both the benchmark and reference implementations are released at https://github.com/rllab/rllab in order to facilitate experimental reproducibility and to encourage adoption by other researchers.

/pdf/benchmarking-deep-reinforcement-learning-for-continuous-vpvt7x30xn.pdf

Benchmarking deep reinforcement learning for continuous control

The 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. The response by the device may include a change of state of the device, and the response may be automatically performed after the user activity is determined.

Automated Response to and Sensing of User Activity in Portable Devices

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 of generating an optimized grammar, for use in speech recognition, from a data set or big list of items, is disclosed. The method includes the steps of obtaining a tree representing items in the data set, and generating the grammar using the tree. The tree or tree data structure representing items in the data set is a simulated recognition search tree, representing items in the data set, which can be automatically generated from the data set.

Method and apparatus for automatic grammar generation from data entries

Controls are provided for a web server to generate client side markups that include recognition and/or audible prompting. The controls comprise elements of a dialog such as a prompt, answer, confirmation, command and validation. An application control provides a means to wrap common speech scenarios in one control.

Application controls for speech enabled recognition

A language processing system may determine a display form of a spoken word by analyzing the spoken form using a language model that includes dictionary entries for display forms of homonyms. The homonyms may include trade names as well as given names and other phrases. The language processing system may receive spoken language and produce a display form of the language while displaying the proper form of the homonym. Such a system may be used in search systems where audio input is converted to a graphical display of a portion of the spoken input.

Speech recognition system with display information

Training data may be provided, the training data including pairs of source phrases and target phrases. The pairs may be used to train an intra-language statistical machine translation model, where the intra-language statistical machine translation model, when given an input phrase of text in the human language, can compute probabilities of semantic equivalence of the input phrase to possible translations of the input phrase in the human language. The statistical machine translation model may be used to translate between queries and listings. The queries may be text strings in the human language submitted to a search engine. The listing strings may be text strings of formal names of real world entities that are to be searched by the search engine to find matches for the query strings.

Intra-language statistical machine translation

A framework for easy and accurate transcription of speech data is provided. Utterances related to a single task are grouped together and processed using combinations of associated sets of recognition results and/or context information in a manner that allows the same transcription for a selected recognition result to be assigned to each of the utterances under consideration.

Yun-Cheng Ju

Papers

Method and apparatus for automatic grammar generation from data entries

Application controls for speech enabled recognition

Speech recognition system with display information

Intra-language statistical machine translation

Transcribing speech data with dialog context and/or recognition alternative information