Acoustic interval detection method and device

A harmonic structure acoustic signal detection method of detecting a segment that includes speech, as a speech segment, from an input acoustic signal, said method comprising:

• an acoustic feature extraction step of extracting an acoustic feature in each of frames into which the input acoustic signal is divided at every predetermined time period;
• and
• a segment determination step of evaluating continuity of the acoustic features and of determining a speech segment according to the evaluated continuity,
• wherein in said acoustic feature extraction step, frequency transform is performed on each of the frames into which the input acoustic signal is divided at every predetermined time period, and the acoustic feature that is a value of a harmonic structure represented by a number is extracted, and
• in said segment determination step, the speech segment is determined based on one of the following:
• a correlation value between acoustic features in the same frame;
• and a correlation value between acoustic features in different frames.

A harmonic structure acoustic signal detection device which detects a segment that includes speech, as a speech segment, from an input acoustic signal, said device comprising:

• an acoustic feature extraction unit operable to extract an acoustic feature in each of frames into which the input acoustic signal is divided at every predetermined time period;
• and
• a segment determination unit operable to evaluate continuity of the acoustic features, and to determine a speech segment according to the evaluated continuity,
• wherein said acoustic feature extraction unit is operable to perform frequency transform on each of the frames into which the input acoustic signal is divided at every predetermined time period, and to extract the acoustic feature that is a value of a harmonic structure represented by a number, and
• said segment determination unit is operable to determine the speech segment based on one of the following:
• a correlation value between acoustic features in the same frame;
• and a correlation value between acoustic features in different frames.

A speech recognition device which recognizes speech included in an input acoustic signal, said device comprising:

• an acoustic feature extraction unit operable to extract an acoustic feature in each of frames into which the input acoustic signal is divided at every predetermined time period;
• a segment determination unit operable to evaluate continuity of the acoustic features, and to determine a speech segment according to the evaluated continuity;
• and
• a recognition unit operable to recognize speech in the speech segment determined by said segment determination unit,
• wherein said acoustic feature extraction unit is operable to perform frequency transform on each of the frames into which the input acoustic signal is divided at every predetermined time period, and to extract the acoustic feature that is a value of a harmonic structure represented by a number, and
• said segment determination unit is operable to determine the speech segment based on one of the following:
• a correlation value between acoustic features in the same frame;
• and a correlation value between acoustic features in different frames.

A speech recording device which records speech included in an input acoustic signal, said device comprising:

• an acoustic feature extraction unit operable to extract an acoustic feature in each of frames into which the input acoustic signal is divided at every predetermined time period;
• a segment determination unit operable to evaluate continuity of the acoustic features, and to determine a speech segment according to the evaluated continuity;
• and
• a recording unit operable to record the input acoustic signal in the speech segment determined by said segment determination unit,
• wherein said acoustic feature extraction unit is operable to perform frequency transform on each of the frames into which the input acoustic signal is divided at every predetermined time period, and to extract the acoustic feature that is a value of a harmonic structure represented by a number, and
• said segment determination unit is operable to determine the speech segment based on one of the following:
• a correlation value between acoustic features in the same frame;
• and a correlation value between acoustic features in different frames.

A program which causes a computer to execute:

• an acoustic feature extraction step of extracting an acoustic feature in each of frames into which the input acoustic signal is divided at every predetermined time period;
• and
• a segment determination step of evaluating continuity of the acoustic features and of determining a speech segment according to the evaluated continuity,
• wherein in said acoustic feature extraction step, frequency transform is performed on each of the frames into which the input acoustic signal is divided at every predetermined time period, and the acoustic feature that is a value of a harmonic structure represented by a number is extracted, and
• in said segment determination step, the speech segment is determined based on one of the following:
• a correlation value between acoustic features in the same frame;
• and a correlation value between acoustic features in different frames.