International Business Machines Corporation

Nuance Communications, Inc.

Michael Daniel Monkowski

Dimitri Kanevsky

Joseph F Shepard

Harry William Printz

Karthik Visweswariah

Jan Sedivy

Satyanarayana Dharanipragada

Michael Alan Picheny

Ponani S Gopalakrishnan

Chengjun Julian Chen

Stephane Herman Maes

Seiki Ogura

Liam David Comerford

Nivo Rovedo

Ramesh Ambat Gopinath

Abraham P Ittycheriah

Jeffrey Scott Sorensen

Peder Andreas Olsen

Patricia A O'Neil

Catalina M Danis

Satya Dharanipragada

A method for implementing pattern matching of integrated circuit features includes computing Voronoi edge regions for both a reference configuration and a search space of an integrated circuit design to be searched and presenting the computed Voronoi edge regions of the reference configuration to a user; receiving one or more selected bisectors of the Voronoi computed reference configuration from the user, indicative of user identified salient regions of design shapes and/or corners to be searched, so as to define one or more search elements, wherein a search element comprises a given bisector and a pair of Voronoi edge regions bounded thereby; constructing a search pattern from the one or more search elements defined from the reference configuration; examining the search space for matching sequences with respect to the search pattern; and highlighting resulting matching patterns in the search space for the user.

Method and system for implementing pattern matching of integrated circuit features using voronoi diagrams

Techniques are provided for generating improved language modeling. Such improved modeling is achieved by conditioning a language model on a state of a dialog for which the language model is employed. For example, the techniques of the invention may improve modeling of language for use in a speech recognizer of an automatic natural language based dialog system. Improved usability of the dialog system arises from better recognition of a user's utterances by a speech recognizer, associated with the dialog system, using the dialog state-conditioned language models. By way of example, the state of the dialog may be quantified as: (i) the internal state of the natural language understanding part of the dialog system; or (ii) words in the prompt that the dialog system played to the user.

Methods and apparatus for generating dialog state conditioned language models

A method for generating a language component vocabulary VC for a speech recognition system having a language vocabulary V of a plurality of word forms is disclosed. The method includes: partitioning the language vocabulary V into subsets of word forms based on frequencies of occurrence of the respective word forms; and in at least one of the subsets, splitting word forms having frequencies less than a threshold to thereby generate word form components. Also disclosed is a method for use in speech recognition including: splitting an acoustic vocabulary comprising baseforms into baseform components and storing the baseform components; and, performing sound to spelling mapping on the baseform components so as to generate a baseform components to word parts table for use in subsequent decoding of speech. A method for decoding a speech utterance using language model components and acoustic components, includes the steps of: generating from the utterance a stack of baseform component paths; concatenating baseform components in a path to generate concatenated baseforms, when the concatenated baseform components correspond to a baseform found in an acoustic vocabulary; mapping the concatenated baseforms into words; computing language model (LM) scores associated with the words using a language model, and performing further decoding of the utterance based thereupon.

System and methods for acoustic and language modeling for automatic speech recognition with large vocabularies

A method for implementing integrated circuit yield estimation includes computing Voronoi regions for an original integrated circuit layout; for each bisector segment of the Voronoi regions and one or more failure mechanisms, computing a failure probability based on geometric parameters of corresponding Voronoi edge regions associated with the bisector segment, using pre-computed failure probabilities as a function of edge orientation and spacing for the failure mechanisms; for each segment of a design edge bounded by bisectors, computing a change in the failure probability based on the geometric parameters of the Voronoi regions, using pre-computed change in failure probabilities for the failure mechanisms; encoding the computed failure probabilities for each Voronoi region in a manner suitable for visual differentiation by a user; and encoding the computed change in failure probabilities by directional displacement of a layout edge segment that would result in a decrease in failure probability.

Implementing integrated circuit yield estimation using voronoi diagrams

Methods and arrangements for generating a voice model in speech processing. Upon accepting at least two input vectors with spectral features, vectors of ranks are created via ranking values of the spectral features of each input vector, ordered vectors are created via arranging the values of each input vector according to rank, and a vector of ordered average values is created via determining the average of corresponding values of the ordered vectors. Thence, a vector of ordered average ranks is created via determining the sum or average of the vectors of ranks, a vector of ordered ranks is created via ranking the values of the ordered average ranks and a spectral feature vector is created via employing the rank order represented by the vector of ordered ranks to reorder the vector of ordered average ranks.

Voice model for speech processing based on ordered average ranks of spectral features

Systems and methods are provided for generating a language component vocabulary VC for a speech recognition system having a language vocabulary V of a plurality of word forms. One method for generating a language component vocabulary VC for a speech recognition system having a language vocabulary V of a plurality of word forms includes partitioning the language vocabulary V into subsets of word forms based on frequencies of occurrence of the respective word forms, in at least one the subsets, splitting word forms having frequencies less than a threshold to thereby generate word form components and generating a language component vocabulary VC including word forms and word form components. The resulting language component vocabulary, which includes word forms and word components, is used to generate a language model that can be efficiently implemented for real-time automatic speech recognition applications for languages with large vocabularies.

Energy normalization in a speech recognition system is achieved by adaptively tracking the high, mid, and low energy envelopes, wherein the adaptive high energy tracking value adapts with weighting enhanced for high energies, and the adaptive low energy tracking value adapts with weighting enhanced for low energies. A tracking method is also provided for discriminating waveform segments as being one of &ldquo;speech&rdquo; or &ldquo;silence&rdquo;, and a measure of the signal to noise ratio and absolute noise floor are used as feedback means to achieve optimal speech recognition accuracy.

Automatic gain control in a speech recognition system

A method of identifying homophones of a word uttered by a user from at least a portion of existing words of a vocabulary of a speech recognition engine comprises the steps of: a user uttering the word; decoding the uttered word; computing respective measures between the decoded word and at least a portion of the other existing vocabulary words, the respective measures indicative of acoustic similarity between the word and the at least a portion of other existing words; if at least one measure is within a threshold range, indicating, to the user, results associated with the at least one measure, the results preferably including the decoded word and the other existing vocabulary word associated with the at least one measure; and the user preferably making a selection depending on the word the user intended to utter.

Apparatus and methods for identifying homophones among words in a speech recognition system

A method of forming a language model for a language having a selected vocabulary of word forms comprises: (a) mapping the word forms into integer vectors in accordance with frequencies of word form occurrence; (b) partitioning the integer vectors into subsets, the subsets respectively having ranges of frequencies of word form occurrence associated therewith, the subsets being arranged in a descending order of frequency ranges; (c) respectively assigning maps to the subsets; (d) filtering a textual corpora using the maps assigned to the subsets in order to generate indexed integers; (e) determining n-gram statistics for the indexed integers; and (f) estimating n-gram language model probabilities from the n-gram statistics to form the language model.

Apparatus and method for forming a filtered inflected language model for

An integrated circuit using high-performance bipolar and CMOS transistor elements on a single chip is fabricated by a simplified process requiring minimal, if any, changes in the process used for forming either type of device in accordance with a variety of possible device designs. The method according to the invention makes maximal use of self-aligned and self-masking processes to reduce the number of processing steps. The number of processing steps is further reduced by performing some steps concurrently on different device types. Further, the masking steps which are employed are reasonably misregistration tolerant, resulting in high manufacturing yield for the process. Consequently, the process according to the invention substantially eliminates the existence of trade-offs between element performance, integration density and process complexity and cost when plural technologies are integrated on the same chip.

High performance/high density BICMOS process

A continuous speech recognition system has the ability to correct errors in strings of words. The error correction method stores data in the system's internal state to update probability tables used in developing alternative lists for substitution in misrecognized text.

Method and apparatus for error correction in a continuous dictation

A method and apparatus for acoustic signal processing of speech recognition, the method comprising the following components: 1) Decompose each syllable into two phonemes of comparable length and complexity, the first one being a preme, and the second one being a toneme; 2) Each toneme is assigned a tone value such as high, rising, low, falling, and untoned; 3) No tone value is assigned to premes; 4) Pitch is detected continuously and treated the same way as energy and cepstrals in a Hidden Markov Model to predict the tone of a toneme; 5) The tone of a syllable is defined as the tone of its component toneme.

Growing community of inventors

New Windsor, NY, United States of America

Michael Daniel Monkowski