Speech synthesis device and method

• US 10,789,937 B2
• Filed: 01/04/2019
• Issued: 09/29/2020
• Est. Priority Date: 10/20/2014
• Status: Active Grant

• Current Assignee: Yamaha Corporation
• Original Assignee: Yamaha Corporation
• Inventors: Kayama, Hiraku, Matsubara, Hiroaki
• Primary Examiner(s): Abebe, Daniel
• Application Number:
  US16/239,891
• Publication Number:
  US 20190139535A1
• Time in Patent Office: 634 Days
• Field of Search: 704275
• CPC Class Codes: G10L 13/0335 Pitch control
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 21/0364 for improving intelligibility
• CPC Class Codes: G10L 25/90 Pitch determination of speech signals

Abstract

This invention is an improvement of technology for automatically generating response voice to voice uttered by a speaker (user), and is characterized by controlling a pitch of the response voice in accordance with a pitch of the speaker'"'"'s utterance. A voice signal of the speaker'"'"'s utterance (e.g., question) is received, and a pitch (e.g., highest pitch) of a representative portion of the utterance is detected. Voice data of a responsive to the utterance is acquired, and a pitch (e.g., average pitch) based on the acquired response voice data is acquired. A pitch shift amount for shifting the acquired pitch to a target pitch having a particular relationship to the pitch of the representative portion is determined. When response voice is to be synthesized on the basis of the response voice data, the pitch of the response voice to be synthesized is shifted in accordance with the pitch shift amount.

Claims

1. A speech synthesis method comprising:

receiving a voice signal of an utterance;

detecting a voiced section of the voice signal;

detecting a pitch of a trailing end portion of the voiced section;

acquiring voice data of a response to the utterance;

acquiring a representative pitch based on the voice data of the response;

determining one shift amount for shifting the representative pitch to a target pitch having a particular relationship to the detected pitch of the trailing end portion; and

synthesizing voice of the response based on the voice data of the response, while shifting pitch of the voice data in accordance with the one shift amount.

2. The speech synthesis method as claimed in claim 1, wherein the voiced section of the voice signal is a portion where a pitch of the voice signal is detectable.

3. The speech synthesis method as claimed in claim 1, wherein the trailing end portion is a part of the voiced section.

4. The speech synthesis method as claimed in claim 1, wherein the trailing end portion has a predetermined time width.

5. The speech synthesis method as claimed in claim 1, wherein the particular relationship is a consonant-interval relationship.

6. A speech synthesis device comprising:

a receiver circuit that receives a voice signal of an utterance; and

a processor configured to;

detect a voiced section of the voice signal;

detect a pitch of a trailing end portion of the voiced section;

acquire voice data of a response to the utterance;

acquire a representative pitch based on the voice data of the response;

determine one shift amount for shifting the representative pitch to a target pitch having a particular relationship to the detected pitch of the trailing end portion; and

synthesize voice of the response based on the voice data of the response, while shifting pitch of the voice data in accordance with the one shift amount.