Nippon Telegraph and Telephone Corporation

Ntt Corporation

Masahiro Yasuda

Yuma Koizumi

Noboru Harada

Even in a case where an amount of training data is small, a caption for an audio signal is generated with high accuracy. An audio caption generation apparatus () generates a caption for an input target audio. A training data storage () stores a training data set including a set of an audio signal and a caption corresponding thereto. An audio similarity calculation unit () calculates similarity between the target audio and each audio signal of training data. A guidance caption retrieval unit () acquires a plurality of captions corresponding to an audio signal similar to the target audio. A caption generation unit () generates a caption for the target audio by determining words in order from the head on the basis of the acquired captions.

Audio caption generation method, audio caption generation apparatus, and program

A direction-of-arrival estimation device for achieving direction-of-arrival estimation which is robust against an SNR and in which an application range of a learning model is specific is provided. The device includes: a reverberation output unit configured to receive input of a real spectrogram extracted from a complex spectrogram of acoustic data and an acoustic intensity vector extracted from the complex spectrogram, and output an estimated reverberation component of the acoustic intensity vector; a noise suppression mask output unit configured to receive input of the real spectrogram and the acoustic intensity vector from which the reverberation component has been subtracted, and output a time frequency mask for noise suppression; and a sound source direction-of-arrival derivation unit configured to derive a sound source direction-of-arrival based on an acoustic intensity vector formed by applying the time frequency mask to the acoustic intensity vector from which the reverberation component has been subtracted.

Direction of arrival estimation apparatus, model learning apparatus, direction of arrival estimation method, model learning method, and program

An input of a first observation signal corresponding to an incoming signal from a first direction is received, an angular rotation operation of the first observation signal is performed to obtain a second observation signal corresponding to an incoming signal from a second direction that is different from the first direction and the second observation signal is added to a set of training data.

Growing community of inventors

Tokyo, Japan

Masahiro Yasuda