Abstract: An information processing device includes a phonetic converting unit, an HMM converting unit, and a searching unit. The phonetic converting unit converts a phonetic symbol sequence into a hidden Markov model (HMM) state sequence in which states of an HMM are aligned. The HMM converting unit converts the HMM state sequence into a score vector sequence indicating the degree of similarity to a specific pronunciation using a similarity matrix defining the similarity between the states of the HMM. The searching unit searches for a path having a better score for the score vector sequence than that of the other paths out of paths included in a search network and outputs a phonetic symbol sequence corresponding to the retrieved path.

Abstract: In an embodiment, a transcription support system includes: a first storage, a playback unit, a second storage, a text generating unit, an estimating unit, and a setting unit. The first storage stores the voice data therein; a playback unit plays back the voice data; and a second storage stores voice indices, each of which associates a character string obtained from a voice recognition process with voice positional information, for which the voice positional information is indicative of a temporal position in the voice data and corresponds to the character string. The text creating unit creates text; the estimating unit estimates already-transcribed voice positional information based on the voice indices; and the setting unit sets a playback starting position that indicates a position at which playback is started in the voice data based on the already-transcribed voice positional information.

Abstract: According to an embodiment, a lattice finalization device finalizes a portion of a lattice that is generated by pattern recognition with respect to a signal on a frame-by-frame basis in chronological order. The device includes a detector and a finalizer. The detector is configured to detect, as a splitting position, a frame in the lattice in which the number of nodes and passing arcs is equal to or smaller than a reference value set in advance. The finalizer is configured to finalize nodes and arcs in paths from a start node to the splitting position in the lattice.

Abstract: According to an embodiment, a data processing device generates result data which represents a result of performing predetermined processing on series data. The device includes an upper-level processor and a lower-level processor. The upper-level processor attaches order information to data blocks constituting the series data. The lower-level processor performs lower-level processing on the data blocks having the order information attached thereto, and attaches common order information, which is in common with the data blocks, to values obtained as a result of the lower-level processing. The upper-level processor integrates the values, which have the common order information attached thereto, based on the common order information and performs upper-level processing to generate the result data.

Abstract: According to an embodiment, a generation device includes a receiver and a generator. The receiver is configured to receive a first model that converts subwords serving as elements of words into the words. The generator is configured to produce, on the basis of the first model, a first finite state transducer that includes a first path having transitions converting one or more subwords into one or more words and a second path, whose first state is the first state of the first path, having cyclic paths to which the subwords are assigned and a transition to which a class classifying a word is assigned.

Abstract: According to an embodiment, an automaton deforming device includes a transforming unit and a deforming unit. The transforming unit generates second values by transforming first values, which either represent weights assigned to transitions in a weighted finite state automaton or represent values that are transformed into weights assigned to transitions in a weighted finite state automaton, in such a way that number of elements of a set of the first values are reduced and an order of the first values is preserved. The deforming unit deforms a weighted finite state automaton in which weights according to the second values are assigned to transitions.

Abstract: In an embodiment, an automaton determinization method includes: state-generating, first-transition-generating, second-transition-generating, and first-deleting. The state-generating includes generating, assigned with a first symbol, a second state newly. The first-transition-generating includes generating a second transition that leaves from the first state and enters to the second state and that is assigned with the first symbol. The second-transition-generating includes generating, regarding the first transitions, a fourth transition where a state previous to a third transition is substituted with the second state. The third transition is an outgoing transition from a next state of the first transition.

Abstract: According to an embodiment, an information processing device includes a first set generating unit that generates a first set of states reachable by following ?-transitions in a forward direction and a reverse direction among states included in a finite state automaton; a second set generating unit that generates a second set representing a set of states included in each of a plurality of first sets connected by one transition that is not an ?-transition and the first set that is not connected to another first set by one transition that is not an ?-transition; a combination generating unit that obtains, among combinations of ?-removal patterns to be respectively applied to the ?-transitions in the second set, a combination with which the number of transitions after removing ?-transitions is the smallest; and a removing unit that removes ?-transitions in the second set by the removal patterns included in the obtained combination.

Abstract: According to one embodiment, a speaker clustering apparatus includes a clustering unit, an extraction unit, and an error detection unit. The clustering unit is configured to extract acoustic features for speakers from an acoustic signal, and to cluster utterances included in the acoustic signal into the speakers by using the acoustic features. The extraction unit is configured to acquire character strings representing contents of the utterances, and to extract linguistic features of the speakers by using the character strings. The error detection unit is configured to decide that, when one of the character strings does not fit with a linguistic feature of a speaker into which an utterance of the one is clustered, the utterance is erroneously clustered by the clustering unit.

Abstract: According to an embodiment, a conversion device converts a first automaton into a second automaton, which both are weighted finite state automatons. The first automaton has a boundary of a path assigned with an input symbol, an appearance position of the boundary, and identifiers for identifying paths. The second automaton has path(s) except unnecessary path(s). The device includes a specifying unit and a search unit. The specifying unit is configured to specify, as a start position, a state of the head of a retrieved path in which a combined weight, which is obtained by adding an accumulated weight from an initial state to the state of the head of the retrieved path in the first automaton and a weight of the best path from the state of the head of the retrieved path to a final state, is best. The search unit is configured to search for a path in which a weight from the start position to a final state in the first automaton is best until reaching next boundary.

Abstract: According to an embodiment, a search device searches paths of a digraph and includes a retriever, and an expander. The retriever is configured to, from among hypotheses stored in a storage, retrieve, as a target hypothesis, a single hypothesis for which a weight obtained by addition of a weight of an already-searched path corresponding to each hypothesis and a weight of the best path from a state of the head of concerned path to a final state is the best weight. The expander is configured to, when the retrieved target hypothesis is not a final hypothesis for which the search has been completed up to a final state, generate new hypotheses each holding an input symbol string that is present in a path in which the search has been performed from states held by the target hypothesis until finding a single input symbol, and write the generated hypotheses in the storage.

Abstract: According to an embodiment, a decoder searches a finite state transducer and outputs an output symbol string corresponding to a signal that is input or corresponding to a feature sequence of signal that is input. The decoder includes a token operating unit and a duplication eliminator. The token operating unit is configured to, every time the signal or the feature is input, propagate each of a plurality of tokens, which is assigned with a state of the head of a path being searched, according to the finite state transducer. The duplication eliminator is configured to eliminate duplication of two or more tokens which have same state assigned thereto and for which respective previously-passed transitions are assigned with same input symbol.

Abstract: According to an embodiment, a decoder includes a token operating unit, a node adder, and a connection detector. The token operating unit is configured to, every time a signal or a feature is input, propagate each of a plurality of tokens, which is an object assigned with a state of the of a path being searched, according to a digraph until a state or a transition assigned with a non-empty input symbol is reached. The node adder is configured to, in each instance of token propagating, add, in a lattice, a node corresponding to a state assigned to each of the plurality of tokens. The connection detector is configured to refer to the digraph and detect a node that is connected to a node added in an i-th instance in the lattice and that is added in an i+1-th instance in the lattice.

Abstract: In an embodiment, an automaton determinization method includes: state-generating, first-transition-generating, second-transition-generating, and first-deleting. The state-generating includes generating, assigned with a first symbol, a second state newly. The first-transition-generating includes generating a second transition that leaves from the first state and enters to the second state and that is assigned with the first symbol. The second-transition-generating includes generating, regarding the first transitions, a fourth transition where a state previous to a third transition is substituted with the second state. The third transition is an outgoing transition from a next state of the first transition.

Abstract: In an embodiment, an automaton determinization method includes: state-generating, first-transition-generating, second-transition-generating, and first-deleting. The state-generating includes generating, assigned with a first symbol, a second state newly. The first-transition-generating includes generating a second transition that leaves from the first state and enters to the second state and that is assigned with the first symbol. The second-transition-generating includes generating, regarding the first transitions, a fourth transition where a state previous to a third transition is substituted with the second state. The third transition is an outgoing transition from a next state of the first transition.

Abstract: According to one embodiment, a finite state transducer determinizing device includes a symbol determination unit, a state merging unit, and a single-value processing unit. The symbol determination unit generates an identification symbol different from an input symbol assigned to each transition of a finite state transducer. The state merging unit extracts one or more states at a transition destination by the same input symbol from among the states of the finite state transducer and generates states having the extracted states as sub-states. The single-value processing unit applies the input symbol assigned to each transition of the finite state transducer or the identification symbol as an input symbol of a transition between the states generated by the state merging unit to perform determinizing.

Abstract: In an embodiment, a retrieving device includes: a text input unit, a first extracting unit, a retrieving unit, a second extracting unit, an acquiring unit, and a selecting unit. The text input unit inputs a text including unknown word information representing a phrase that a user was unable to transcribe. The first extracting unit extracts related words representing a phrase related to the unknown word information among phrases other than the unknown word information included in the text. The retrieving unit retrieves a related document representing a document including the related words. The second extracting unit extracts candidate words representing candidates for the unknown word information from a plurality of phrases included in the related document. The acquiring unit acquires reading information representing estimated pronunciation of the unknown word information. The selecting unit selects at least one of candidate word of which pronunciation is similar to the reading information.

Abstract: According to an embodiment, an information processing apparatus includes a storage unit, a detector, an acquisition unit, and a search unit. The storage unit configured to store therein voice indices, each of which associates a character string included in voice text data obtained from a voice recognition process with voice positional information, the voice positional information indicating a temporal position in the voice data and corresponding to the character string. The acquisition unit acquires reading information being at least a part of a character string representing a reading of a phrase to be transcribed from the voice data played back. The search unit specifies, as search targets, character strings whose associated voice positional information is included in the played-back section information among the character strings included in the voice indices, and retrieves a character string including the reading represented by the reading information from among the specified character strings.

Abstract: According to an embodiment, an information processing device includes a first set generating unit that generates a first set of states reachable by following ?-transitions in a forward direction and a reverse direction among states included in a finite state automaton; a second set generating unit that generates a second set representing a set of states included in each of a plurality of first sets connected by one transition that is not an ?-transition and the first set that is not connected to another first set by one transition that is not an ?-transition; a combination generating unit that obtains, among combinations of ?-removal patterns to be respectively applied to the ?-transitions in the second set, a combination with which the number of transitions after removing ?-transitions is the smallest; and a removing unit that removes ?-transitions in the second set by the removal patterns included in the obtained combination.

Abstract: In an embodiment, an automaton determinization method includes: state-generating, first-transition-generating, second-transition-generating, and first-deleting. The state-generating includes generating, assigned with a first symbol, a second state newly. The first-transition-generating includes generating a second transition that leaves from the first state and enters to the second state and that is assigned with the first symbol. The second-transition-generating includes generating, regarding the first transitions, a fourth transition where a state previous to a third transition is substituted with the second state. The third transition is an outgoing transition from a next state of the first transition.