Abstract: A computer-implemented method of detecting a portion of audio data to be removed is provided. The method includes obtaining a recognition result of audio data. The recognition result includes recognized text data and time stamps. The method also includes extracting one or more candidate phrases from the recognition result using n-gram counts. The method further includes, for each candidate phrase, making pairs of same phrases with different time stamps and clustering the pairs of the same phrase by using differences in time stamps. The method includes further determining a portion of the audio data to be removed using results of the clustering.

Abstract: Symbol sequences are estimated using a computer-implemented method including detecting one or more candidates of a target symbol sequence from a speech-to-text data, extracting a related portion of each candidate from the speech-to-text data, detecting repetition of at least a partial sequence of each candidate within the related portion of the corresponding candidate, labeling the detected repetition with a repetition indication, and estimating whether each candidate is the target symbol sequence, using the corresponding related portion including the repetition indication of each of the candidates.

Abstract: A technique for training a model is disclosed. A training sample including an input sequence of observations and a target sequence of symbols having length different from the input sequence of observations is obtained. The input sequence of observations is fed into the model to obtain a sequence of predictions. The sequence of predictions is shifted by an amount with respect to the input sequence of observations. The model is updated based on a loss using a shifted sequence of predictions and the target sequence of the symbols.

Abstract: A technique for estimating phonemes for a word written in a different language is disclosed. A sequence of graphemes of a given word in a source language is received. The sequence of the graphemes in the source language is converted into a sequence of phonemes in the source language. One or more sequences of phonemes in a target language are generated from the sequence of the phonemes in the source language by using a neural network model. One sequence of phonemes in the target language is determined for the given word. Also, technique for estimating graphemes of a word from phonemes in a different language is disclosed.

Abstract: A method for reducing response time in a speech interface including constructing a partially completed word sequence from a partially received utterance from a speaker received by an audio sensor, modeling a remainder portion using a processor based on a rich predictive model to predict the remainder portion, and responding to the partially completed word sequence and the predicted remainder portion using a natural language vocalization generator with a vocalization, wherein the vocalization is prepared before a complete utterance is received from the speaker and conveyed to the speaker by an audio transducer.

Abstract: A computer-implemented method for generating a text is disclosed. The method includes obtaining a first text collection matched with a target domain and a second text collection including a plurality of samples, each of which describes rewriting between a first text and a second text that has a style different from the first text. The method also includes training a text generation model with the first text collection and the second text collection, in which the text generation model has, in a vocabulary, one or more operation tokens indicating rewriting. The method further includes outputting a plurality of texts obtained from the text generation model.

Abstract: A computer-implemented method includes generating a single text data structure for a classifier of a speech recognition system, and sending the single text data structure to the classifier. Generating the single text data structure includes obtaining n-best hypotheses as an output of an automatic speech recognition (ASR) task for an utterance received by the speech recognition system, and combining the n-best hypotheses in a predetermined order with a separator between each pair of hypotheses to generate the single text data structure. The classifier is trained based on a single training text data structure by obtaining training source data, including selecting a first text sample and at least one similar text sample belong to a same class as the first text sample based on a maximum number of hypotheses, and arranging the plurality of text samples based on a degree of similarity.

Abstract: A computer-implemented method is provided for generating a plurality of templates. The method includes obtaining, by a processor device, a Recurrent Neural Network Language Model (RNNLM) trained using a first set of text data. The method further includes adapting, by the processor device, the RNNLM using a second set of text data by adding a new node corresponding to a class in both an input layer and an output layer of the RNNLM, the class being obtained from the second set of text data. The method also includes generating, by the processor device, the plurality of templates using the adapted RNNLM.

Abstract: A computer-implemented method for training a model is disclosed. The model is capable of retaining a history of one or more preceding elements and has a direction of prediction. The method includes obtaining a training sequence of elements. The method also includes splitting the training sequence into a plurality of parts. The method further includes selecting one part of the plurality of the parts depending on the direction of the model to generate a modified training data. The method includes further training the model using the modified training data.

Abstract: A method, system, and computer program product for learning a recognition model for recognition processing. The method includes preparing one or more examples for learning, each of which includes an input segment, an additional segment adjacent to the input segment and an assigned label. The input segment and the additional segment are extracted from an original training data. A classification model is trained, using the input segment and the additional segment in the examples, to initialize parameters of the classification model so that extended segments including the input segment and the additional segment are reconstructed from the input segment. Then, the classification model is tuned to predict a target label, using the input segment and the assigned label in the examples, based on the initialized parameters. At least a portion of the obtained classification model is included in the recognition model.

Abstract: An apparatus, method, and computer program product for adapting an acoustic model to a specific environment are defined. An adapted model obtained by adapting an original model to the specific environment using adaptation data, the original model being trained using training data and being used to calculate probabilities of context-dependent phones given an acoustic feature. Adapted probabilities obtained by adapting original probabilities using the training data and the adaptation data, the original probabilities being trained using the training data and being prior probabilities of context-dependent phones. An adapted acoustic model obtained from the adapted model and the adapted probabilities.

Abstract: A computer implemented method for training a neural network to capture a structural feature specific to a set of chemical compounds is disclosed. In the method, the computer system reads an expression describing a structure of the chemical compound for each chemical compound in the set and enumerates one or more combinations of a position and a type of a structural element appearing in the expression for each chemical compound in the set. The computer system also generates training data based on the one or more enumerated combinations for each chemical compound in the set. The training data includes one or more values with a length, each of which indicates whether or not a corresponding type of the structural element appears at a corresponding position for each combination. Furthermore, the computer system trains the neural network based on the training data for the set of the chemical compounds.

Abstract: A technique for aligning spike timing of models is disclosed. A first model having a first architecture trained with a set of training samples is generated. Each training sample includes an input sequence of observations and an output sequence of symbols having different length from the input sequence. Then, one or more second models are trained with the trained first model by minimizing a guide loss jointly with a normal loss for each second model and a sequence recognition task is performed using the one or more second models. The guide loss evaluates dissimilarity in spike timing between the trained first model and each second model being trained.

Abstract: An apparatus, method, and computer program product for adapting an acoustic model to a specific environment are defined. An adapted model obtained by adapting an original model to the specific environment using adaptation data, the original model being trained using training data and being used to calculate probabilities of context-dependent phones given an acoustic feature. Adapted probabilities obtained by adapting original probabilities using the training data and the adaptation data, the original probabilities being trained using the training data and being prior probabilities of context-dependent phones. An adapted acoustic model obtained from the adapted model and the adapted probabilities.

Abstract: A technique for data augmentation for speech data is disclosed. Original speech data including a sequence of feature frames is obtained. A partially prolonged copy of the original speech data is generated by inserting one or more new frames into the sequence of the feature frames. The partially prolonged copy is output as augmented speech data for training an acoustic model for training an acoustic model.

Abstract: A computer implemented method for training a neural network to capture a structural feature specific to a set of chemical compounds is disclosed. In the method, the computer system reads an expression describing a structure of the chemical compound for each chemical compound in the set and enumerates one or more combinations of a position and a type of a structural element appearing in the expression for each chemical compound in the set. The computer system also generates training data based on the one or more enumerated combinations for each chemical compound in the set. The training data includes one or more values with a length, each of which indicates whether or not a corresponding type of the structural element appears at a corresponding position for each combination. Furthermore, the computer system trains the neural network based on the training data for the set of the chemical compounds.

Abstract: A computer-implemented method, computer program product, and system are provided for separating a word in a dictionary. The method includes reading a word from the dictionary as a source word. The method also includes searching the dictionary for another word having a substring with a same surface string and a same reading as the source word. The method additionally includes splitting the another word by the source word to obtain one or more remaining substrings of the another word. The method further includes registering each of the one or more remaining substrings as a new word in the dictionary.

Abstract: Fusion of neural networks is performed by obtaining a first neural network and a second neural network. The first and the second neural networks are the result of a parent neural network subjected to different training. A similarity score is calculated of a first component of the first neural network and a corresponding second component of the second neural network. An interpolation weight is determined for the first and the second components by using the similarity score. A neural network parameter of the first component is updated based on the interpolation weight and a corresponding neural network parameter of the second component to obtain a fused neural network.

Abstract: A computer-implemented method, computer program product, and apparatus are provided. The method includes generating a plurality of sequences of small unit tokens from a first language model that is trained with a small unit corpus including the small unit tokens, the small unit corpus having been derived by tokenization with a small unit. The method further includes tokenizing the plurality of sequences of small unit tokens by a large unit that is larger than the small unit, to create a derived large unit corpus including derived large unit tokens.

Abstract: A computer-implemented method for training a model is disclosed. The model is capable of retaining a history of one or more preceding elements and has a direction of prediction. The method includes obtaining a training sequence of elements. The method also includes splitting the training sequence into a plurality of parts. The method further includes selecting one part of the plurality of the parts depending on the direction of the model to generate a modified training data. The method includes further training the model using the modified training data.