Abstract: Disclosed are a method, a system and a computer program for translating an application simulation into a plurality of languages. The method comprises the steps of creating a first simulation having a sequence of frames, in a first language; adding elements in said first language to said sequence of frames; and creating a second simulation having a sequence of frames in a second language. The method comprises the further steps of exporting said elements including frame sequence number, position of each of said elements, and settings to a document; translating said elements in said document into said second language; and automatically placing the translated elements on said frames of said second simulation, using said sequence numbers, said position, and said settings.

Abstract: Representation-neutral dialogue systems and methods (“RNDS”) are described that include multi-application, multi-device spoken-language dialogue systems based on the information-state update approach. The RNDS includes representation-neutral core components of a dialogue system that provide scripted domain-specific extensions to routines such as dialogue move modeling and reference resolution, easy substitution of specific semantic representations and associated routines, and clean interfaces to external components for language-understanding (i.e., speech-recognition and parsing) and language-generation, and to domain-specific knowledge sources. The RNDS also resolves multi-device dialogue by evaluating and selecting among candidate dialogue moves based on features at multiple levels. Multiple sources of information are combined, multiple speech recognition and parsing hypotheses tested, and multiple device and moves considered to choose the highest scoring hypothesis overall.

Abstract: An approach to wordspotting (180) using query data from one or more spoken instance of a query (140). The query data is processed to determining a representation of the query (160) that defines multiple sequences of subword (130) units each representing the query. Then putative instances of the query (190) are located in input data from an audio signal using the determined representation of the query.

Abstract: Disclosed herein are a system and method for trend prediction of signals in a time series using a Markov model. The method includes receiving a plurality of data series and input parameters, where the input parameters include a time step parameter, preprocessing the plurality of data series according to the input parameters, to form binned and classified data series, and processing the binned and classified data series. The processing includes initializing a Markov model for trend prediction, and training the Markov model for trend prediction of the binned and classified data series to form a trained Markov model. The method further includes deploying the trained Markov model for trend prediction, including outputting trend predictions. The method develops an architecture for the Markov model from the data series and the input parameters, and disposes the Markov model, having the architecture, for trend prediction.

Abstract: A method for automatic speech recognition includes determining for an input signal a plurality scores representative of certainties that the input signal is associated with corresponding states of a speech recognition model, using the speech recognition model and the determined scores to compute an average signal, computing a difference value representative of a difference between the input signal and the average signal, and processing the input signal in accordance with the difference value.

Abstract: A system and method for generating synthetic speech, which operates in a computer implemented Text-To-Speech system. The system comprises at least a speaker database that has been previously created from user recordings, a Front-End system to receive an input text and a Text-To-Speech engine. The Front-End system generates multiple phonetic transcriptions for each word of the input text, and the TTS engine uses a cost function to select which phonetic transcription is the more appropriate for searching the speech segments within the speaker database to be concatenated and synthesized.

Abstract: The invention relates to a method for supporting an encoding of an audio signal, wherein at least one section of the audio signal is to be encoded with a coding model that allows the use of different coding frame lengths. In order to enable a simple selection of the respectively best suited coding frame length, it is proposed that at least one control parameter is determined based on signal characteristics of the audio signal. The control parameter is then used for limiting the options of possible coding frame lengths for the at least one section. The invention relates equally to a module 10,11 in which this method is implemented, to a device 1 and a system comprising such a module 10,11, and to a software program product including a software code for realizing the proposed method.

Abstract: In one embodiment, distortion in a received speech signal is estimated using at least one model trained based on subjective quality assessment data. A speech quality assessment for the received speech signal is then determined based on the estimated distortion.

Abstract: Provided is a method for converting a dimension of a vector. The vector dimension conversion method for vector quantization includes the steps of: extracting a specific parameter having a pitch period from an input speech signal and then generating a vector of a dimension that varies according to the pitch period; dividing an entire frequency domain of the generated vector of the variable dimension into at least two frequency domains; and converting the vector of the variable dimension into vectors of mutually different fixed dimensions according to the divided frequency domains. Thereby, not only an error due to the vector dimension conversion is suppressed but codebook memory required for the vector quantization is effectively reduced.

Abstract: A method for implementing speech focus in a speech processing system can include the step of establishing a default focus receiver as a first entity to request speech focus of a speech processing system having multiple applications that share speech resources based upon speech focus. An event occurrence can be detected. An event handler of the default speech receiver can previously define behavior for the event occurrence and where default system behavior can be implemented within the speech processing system for the event occurrence. The default system behavior can be utilized when speech focus is not assigned during the event occurrence. Responsive to the event occurrence, at least one programmatic action can be performed in accordance with machine readable instructions of the event handler. The default system behavior is not implemented responsive to the event occurrence.

Abstract: Techniques are disclosed for facilitating the process of proofreading draft transcripts of spoken audio streams. In general, proofreading of a draft transcript is facilitated by playing back the corresponding spoken audio stream with an emphasis on those regions in the audio stream that are highly relevant or likely to have been transcribed incorrectly. Regions may be emphasized by, for example, playing them back more slowly than regions that are of low relevance and likely to have been transcribed correctly. Emphasizing those regions of the audio stream that are most important to transcribe correctly and those regions that are most likely to have been transcribed incorrectly increases the likelihood that the proofreader will accurately correct any errors in those regions, thereby improving the overall accuracy of the transcript.

Abstract: Methods are disclosed for automatic accent labeling without manually labeled data. The methods are designed to exploit accent distribution between function and content words.

Abstract: A speech segment is indexed by identifying at least two alternative word sequences for the speech segment. For each word in the alternative sequences, information is placed in an entry for the word in the index. Speech units are eliminated from entries in the index based on a comparison of a probability that the word appears in the speech segment and a threshold value.

Abstract: A method of measuring the degree of enhancement made to a voice signal by receiving the voice signal, identifying formant regions in the voice signal, computing stationarity for each identified formant region, enhancing the voice signal, identifying formant regions in the enhanced voice signal that correspond to those identified in the received voice signal, computing stationarity for each formant region identified in the enhanced voice signal, comparing corresponding stationarity results for the received and enhanced voice signals, and calculating at least one user-definable statistic of the comparison results as the degree of enhancement made to the received voice signal.

Abstract: An apparatus and method encode audio data, and an apparatus and method decode encoded audio data. An audio data encoding apparatus includes: a scalable encoding unit dividing audio data into a plurality of layers, representing the audio data in predetermined numbers of bits in each of the plurality of layers, and encoding a lower layer prior to encoding an upper layer and an upper bit of each layer prior to encoding a lower bit of each layer; an SBR encoding unit generating spectral band replication (SBR) data that has information with respect to audio data in a frequency band of frequencies equal to or greater than a predetermined frequency among the audio data to be encoded, and encoding the SBR data; and a bitstream production unit generating a bitstream using the encoded SBR data and the encoded audio data corresponding to a predetermined bitrate.

Abstract: An index for searching spoken documents having speech data and text meta-data is created by obtaining probabilities of occurrence of words and positional information of the words of the speech data and combining it with at least positional information of the words in the text meta-data. A single index can be created because the speech data and the text meta-data are treated the same and considered only different categories.

Abstract: An apparatus, method, and medium for detecting a voiced sound and an unvoiced sound. The apparatus includes a blocking unit for dividing an input signal into block units; a parameter calculator for calculating a first parameter to determine the voiced sound and a second parameter to determine the unvoiced sound by using a slope and spectral flatness measure (SFM) of a mel-scaled filter bank spectrum of an input signal existing in a block; and a determiner for determining a voiced sound zone and an unvoiced sound zone in the block by comparing the first and second parameters to predetermined threshold values.

Abstract: A system for retrieving documents related to a concept from a text corpus includes a set of stored semantic classes which are combinable to express the concept each class including a set of keywords, each set of keywords including at least one keyword. Syntactic rules are applied to identified text portions which include one or more of the keywords. A rule is satisfied when keywords from the first and second semantic classes are in any one of a plurality of syntactic relationships. A concept matching module identifies text portions within the text corpus which include one or more of the keywords, for applying the syntactic rules to the text portions, and for identifying those text portions which satisfy at least one of the rules. Documents to be retrieved may include at least one of the identified text portions.

Abstract: A reliable full covariance matrix estimation algorithm for pattern unit's state output distribution in pattern recognition system is discussed. An intermediate hierarchical tree structure is built to relate models for product units. Full covariance matrices of pattern unit's state output distribution are estimated based on all the related nodes in the tree.

Abstract: An audio data processing device including: a first processor; and a second processor which is connected to the first processor wherein the first processor includes: an audio data acquisition which acquires audio data of digital data; an omitting section which omits a bit corresponding to low volume which is hard to be heard by human ears from the audio data; and a transmitter which transmits the audio data in which the bit corresponding to the low volume is omitted by the omitting section from the first processor to the second processor; wherein the second processor includes: a receiver which receives the audio data transmitted from the first processor; and a reproduction data generator which generates audio reproduction data necessary to reproduce the audio data based on the received audio data.