Kabushiki Kaisha Toshiba

Daichi Hayakawa

Takehiko Kagoshima

Hiroshi Fujimura

Kenji Iwata

According to one embodiment, a speech recognition apparatus includes processing circuitry. The processing circuitry generates a plurality of augmented speech data, based on input speech data, generates a plurality of acoustic scores, based on the plurality of augmented speech data and an acoustic model, generates a plurality of adjusted acoustic scores by resampling the acoustic scores, generates an integrated acoustic score by integrating the adjusted acoustic scores, generates an integrated lattice, based on the integrated acoustic score, a pronunciation dictionary, and a language model, and searches a speech recognition result with a highest likelihood from the integrated lattice.

Speech recognition apparatus and method

According to one embodiment, a speech recognition apparatus includes processing circuitry. The processing circuitry generates, based on sensor information, environmental information relating to an environment in which the sensor information has been acquired, generates, based on the environmental information and generic speech data, an adapted acoustic model obtained by adapting a base acoustic model to the environment, acquires speech uttered in the environment as input speech data, and subjects the input speech data to a speech recognition process using the adapted acoustic model.

Speech recognition apparatus, method and non-transitory computer-readable storage medium

A signal processing apparatus according an embodiment includes an acquisition unit and an application unit. The acquisition unit acquires M detection signals output from M detector devices having N-fold symmetry (M is an integer equal to or greater than 2, and N is an integer equal to or greater than 2). Each of the M detector devices detects original signals generated from K signal sources (K is an integer equal to or greater than 2) having the N-fold symmetry. The application unit applies a trained neural network to M input vectors corresponding to the M detection signals and outputs K output vectors. The same parameter is set to, of multiple weights included in a weight matrix of the trained neural network, weights that are commutative based on the N-fold symmetry.

Signal processing apparatus and non-transitory computer readable medium

According to one embodiment, a signal generation device includes one or more processors. The processors convert an acoustic signal and output amplitude and phase at a plurality of frequencies. The processors, for each of a plurality of nodes of a hidden layer included in a neural network that treats the amplitude and the phase as input, obtain frequency based on a plurality of weights used in arithmetic operation of the node. The processors generate an acoustic signal based on the plurality of obtained frequencies and based on amplitude and phase corresponding to each of the plurality of nodes.

Acoustic signal processing with neural network using amplitude, phase, and frequency

A signal processing apparatus includes one or more processors. The processors acquire a plurality of observed signals acquired from a plurality of microphone groups each including at least one microphone selected from a plurality of microphones. The microphone groups include respective microphone combinations each including at least one microphone, the combinations are different from each other, and at least one of the microphone groups includes a plurality of microphones. The processors estimate a mask indicating occupancy for each of time frequency points of a sound signal of a space corresponding to the observed signal in a plurality of spaces, for each of the observed signals. The processors integrate masks estimated for the observed signals to generate an integrated mask indicating occupancy for each of time frequency points of a sound signal in a space determined based on the spaces.

Growing community of inventors

Chiba, Japan

Daichi Hayakawa