Synthetic speech text-input device and program

• US 8,504,368 B2
• Filed: 09/10/2010
• Issued: 08/06/2013
• Est. Priority Date: 09/10/2009
• Status: Active Grant

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: Katae, Nobuyuki, Murase, Kentaro
• Primary Examiner(s): Godbold, Douglas
• Application Number:
  US12/879,299
• Publication Number:
  US 20110060590A1
• Time in Patent Office: 1,061 Days
• Field of Search: 704258-269
• US Class Current: 704/260
• CPC Class Codes: G10L 13/10 Prosody rules derived from text; Stress or intonation
• CPC Class Codes: G11B 27/034 on discs G11B27/036, G11B27/038 take precedence
• CPC Class Codes: G11B 27/10 Indexing; Addressing; Timing or synchronising; Measuring tape travel

Abstract

A synthetic speech text-input device is provided that allows a user to intuitively know an amount of an input text that can be fit in a desired duration. A synthetic speech text-input device 1 includes: an input unit that receives a set duration in which a speech to be synthesized is to be fit, and a text for a synthetic speech; a text amount calculation unit that calculates an acceptable text amount based on the set duration received by the input unit, the acceptable text amount being an amount of a text acceptable as a synthetic speech of the set duration; and a text amount output unit that outputs the acceptable text amount calculated by the text amount calculation unit, when the input unit receives the text.

Claims

1. A synthetic speech text-input device, comprising:

an input unit that receives a set duration in which a speech to be synthesized is to be fit, and a text for a synthetic speech;

a text amount calculation unit that calculates an acceptable input text amount based on the set duration received by the input unit, the acceptable input text amount being an amount of an input text acceptable as a synthetic speech of the set duration; and

a text amount output unit that outputs the acceptable input text amount calculated by the text amount calculation unit, when the input unit receives the text for a synthetic speech.

2. The synthetic speech text-input device according to claim 1,

wherein the input unit further receives an utterance speed of the synthetic speech, and

the text amount calculation unit calculates the acceptable input text amount, further based on the utterance speed received by the input unit.

3. The synthetic speech text-input device according to claim 1, further comprising a speech synthesis unit that converts the text received by the input unit into a synthetic speech,

wherein the speech synthesis unit calculates a duration of a partial synthetic speech corresponding a text portion received already by the input unit, and

the text amount calculation unit corrects the acceptable input text amount, using the duration of the partial synthetic speech calculated by the speech synthesis unit.

4. The synthetic speech text-input device according to claim 1, further comprising a speech synthesis unit that converts the text received by the input unit into a synthetic speech

wherein the speech synthesis includes:

a linguistic processing section that analyzes the text received by the input unit, and generates an intermediate expression that includes reading information of the text;

a prosody generation section that generates a duration of a synthetic speech corresponding to the text, and a pitch pattern as a variation pattern of a pitch of the synthetic speech corresponding to the text, from the intermediate expression generated by the linguistic processing section; and

a waveform generation section that generates a synthetic speech, based on the duration of the synthetic speech corresponding to the text and the pitch pattern as a variation pattern of a pitch of the synthetic speech corresponding to the text, the duration and the pitch pattern being generated by the prosody generation section,

wherein the text amount calculation unit calculates the acceptable input text amount, further using the duration of the synthetic speech calculated by the prosody generation section of the speech synthesis unit.

5. The synthetic speech text-input device according to claim 1, further comprising:

a speech synthesis unit that converts the text received by the input unit into a synthetic speech; and

a calculation formula changing unit,

wherein the speech synthesis unit generates partial reading information of a text portion received already by the input unit, and a duration of a partial synthetic speech corresponding the text portion, and

the text amount calculation unit calculates the acceptable input text amount by substituting the set duration in a predetermined calculation formula,

the calculation formula changing unit changes the calculation formula, based on at least either one of the partial reading information and the duration of the partial synthetic speech generated by the speech synthesis unit.

6. The synthetic speech text-input device according to claim 1,

wherein the text amount calculation unit calculates an upper limit and a lower limit of the acceptable input text amount, and

the text amount output unit outputs a range of the acceptable input text amount expressed with the upper limit and the lower limit calculated by the text amount calculation unit.

7. The synthetic speech text-input device according to claim 1, wherein the input unit receives, from a user, a designation of at least a part of sections of video data, and sets a duration corresponding to the designated section as the set duration.

8. The synthetic speech text-input device according to claim 1, further comprising a speech synthesis unit that converts the text received by the input unit into a synthetic speech,

wherein the speech synthesis unit includes:

a linguistic processing section that analyzes the text received by the input unit, and generates an intermediate expression that includes reading information of the text;

a prosody generation section that generates a duration of a synthetic speech corresponding to the text, and a pitch pattern as a variation pattern of a pitch of the synthetic speech corresponding to the text, from the intermediate expression generated by the linguistic processing section;

a waveform generation section that generates a synthetic speech, based on the duration of the synthetic speech corresponding to the text, and the pitch pattern as a variation pattern of a pitch of the synthetic speech corresponding to the text, the duration and the pitch pattern being generated by the prosody generation section; and

a prosody correction unit that extends or shortens the duration of the synthetic speech generated by the prosody generation section, or extends or shortens a duration of a pause included in the synthetic speech, so that the duration of the synthetic speech approaches the set duration.

9. The synthetic speech text-input device according to claim 1, further comprising:

a speech synthesis unit that converts the text received by the input unit into a synthetic speech;

a video data input unit that inputs video data including a section that is to be synchronized with a synthetic speech of the text received by the input unit; and

a video-speech synchronization unit that edits video data so that a duration of the synthetic speech obtained by conversion by the speech synthesis unit approaches the set duration.

10. A non-transitory computer-readable recording medium storing synthetic speech text-input program that allows a computer to execute:

input processing that receives a set duration in which a speech to be synthesized is to be fit, and a text for a synthetic speech;

text amount calculation processing that calculates an acceptable input text amount based on the set duration received by the input processing, the acceptable input text amount being an amount of an input text acceptable as a synthetic speech of the set duration; and

text amount output processing that outputs the acceptable input text amount calculated by the text amount calculation processing, when the input processing receives the text.