Intonation adjustment in text-to-speech systems

• US 5,642,466 A
• Filed: 01/21/1993
• Issued: 06/24/1997
• Est. Priority Date: 01/21/1993
• Status: Expired due to Term

• Current Assignee: Apple Inc.
• Original Assignee: Apple Computer Incorporated (Apple Inc.)
• Inventors: Narayan, Shankar
• Primary Examiner(s): Moore, David K.
• Assistant Examiner(s): HAFIZ, TARIQ R
• Application Number:
  US08/007,188
• Time in Patent Office: 1,615 Days
• Field of Search: 381/36-38, 381/48-52, 395/2, 395/2.1, 395/2.14-2.16, 395/2.67, 395/2.71, 395/2.69, 395/2.76
• US Class Current: 704/260
• CPC Class Codes: G10L 13/10 Prosody rules derived from text; Stress or intonation

Abstract

A software-only real time text-to-speech system includes intonation control which does not introduce discontinuities into output speech stream. The text-to-speech system includes a module for translating text to a sequence of sound segment codes and intonation control signals. A decoder is coupled to the translator to produce sets of digital frames of speech data, which represent sounds for the respective sound segment codes in the sequence. An intonation control system is responsive to intonation control signals for modifying a block of one or more frames in the sets of frames of speech data to generate a modified block. The modified block substantially preserves the continuity of the beginning and ending segments of the block with adjacent frames in the sequence. Thus, when the modified block is inserted in the sequence, no discontinuities are introduced and smooth intonation control is accomplished. The intonation control system provides for both pitch and duration control.

Claims

1. An apparatus for adjusting an intonation of a sound wherein the sound is specified by a sequence of frames each comprising a set of digital samples, the apparatus comprising:

means for receiving a set of intonation control signals that indicate a pitch adjustment and a duration adjustment to the sound;

buffer that stores the sequence of frames;

intonation control means that generates an intonation adjusted sequence of frames by accessing a block of one or more frames of the sequence of frames from the buffer and by generating a modified block in response to the intonation control signals and by inserting the modified block into the sequence of frames wherein the intonation control means minimizes discontinuity between a beginning segment and an ending segment of the block and a pair of adjacent frames in the intonation adjusted sequence of frames, wherein the intonation control signals indicate a change in a nominal length of a specified frame of the sequence of frames to indicate the pitch adjustment and indicate a change in a number of frames in the sequence of frames to indicate the duration adjustment, and wherein the intonation control means includes

pitch lowering means for increasing a length N of the specified frame by an amount equal to Δ

samples wherein the block of one or more frames consists of the specified frame, the pitch lowering means including means for applying a first weighting function to the block emphasizing the beginning segment to generate a first vector and means for applying a second weighting function to the block emphasizing the ending segment to generate a second vector and means for combining the first vector with the second vector shifted by Δ

samples to generate the modified block having a length N+Δ

,

pitch raising means for decreasing the length N of the specified frame by an amount equal to Δ

samples wherein the block of one or more frames consists of the specified frame and a next frame having a length NR in the sequence of frames, the pitch raising means including means for applying the first weighting function to the block emphasizing the beginning segment to generate the first vector and means for applying the second weighting function to the block emphasizing the ending segment to generate the second vector and means for combining the first vector with the second vector shifted by Δ

samples to generate a shortened frame with the next frame to generate the modified block having a length N-Δ

+NR,

duration shortening means for modifying the block to reduce the number of frames in the sequence of frames wherein the block consists of a pair of sequential frames having lengths NL and NR respectively, the duration shortening means including means for applying the first weighting function to the block emphasizing the beginning segment to generate the first vector and means for applying the second weighting function to the block emphasizing the ending segment to generate the second vector and means for combining the first vector with the second vector to generate the modified block having the length NL or the length NR, and

duration lengthening means for modifying the block to increase the number of frames in the sequence of frames wherein the block consists of a pair of left and right sequential frames having the lengths NL and NR respectively, the duration lengthening means including means for applying the first weighting function to the block emphasizing the beginning segment to generate the first vector and means for applying the second weighting function to the block emphasizing the ending segment to generate the second vector and means for combining the first vector with the second vector to generate a new frame and means for concatenating the left frame, the new frame, and the right frame to generate the modified block.

2. An apparatus for adjusting an intonation of a sound wherein the sound is specified by a sequence of frames each comprising a set of digital samples, the apparatus comprising:

means for receiving a set of intonation control signals that indicate a pitch adjustment and a duration adjustment to the sound;

buffer that stores the sequence of frames;

intonation control means that generates an intonation adjusted sequence of frames by accessing a block of one or more frames of the sequence of frames from the buffer and by generating a modified block in response to the intonation control signals and by inserting the modified block into the sequence of frames such that the intonation control frames minimizes a discontinuity between a beginning segment and an ending segment of the block and a pair of adjacent frames in the intonation adjusted sequence of frames;

wherein the intonation control signals indicate a change in a nominal length of a specified frame of the sequence of frames to indicate the pitch adjustment and indicate a change in a number of frames in the sequence of frames to indicate the duration adjustment and,

wherein the intonation control means includes pitch lowering means for increasing a length N of the specified frame by an amount equal to Δ

samples wherein the block of one or more frames consists of the specified frame, the pitch lowering means including means for applying a first weighting function to the block emphasizing the beginning segment to generate a first vector and means for applying a second weighting function to the block emphasizing the ending segment to generate a second vector and means for combining the first vector with the second vector shifted by Δ

samples to generate the modified block having a length N+Δ

.

3. An apparatus for adjusting an intonation of a sound wherein the sound is specified by a sequence of frames each comprising a set of digital samples, the apparatus comprising:

means for receiving a set of intonation control signals that indicate a pitch adjustment and a duration adjustment to the sound;

buffer that stores the sequence of frames;

intonation control means that generates an intonation adjusted sequence of frames by accessing a block of one or more frames of the sequence of frames from the buffer and by generating a modified block in response to the intonation control signals and by inserting the modified block into the sequence of frames such that the intonation control frames minimizes a discontinuity between a beginning segment and an ending segment of the block and a pair of adjacent frames in the intonation adjusted sequence of frames;

wherein the intonation control signals indicate a change in a nominal length of a specified frame of the sequence of frames to indicate the pitch adjustment and indicate a change in a number of frames in the sequence of frames to indicate the duration adjustment and,

wherein the intonation control means includes pitch raising means for decreasing a length N of the specified frame by an amount equal to Δ

samples wherein the block of one or more frames consists of the specified frame and a next frame having a length NR in the sequence of frames, the pitch raising means including means for applying a first weighting function to the block emphasizing the beginning segment to generate a first vector and means for applying a second weighting function to the block emphasizing the ending segment to generate a second vector and means for combining the first vector with the second vector shifted by Δ

samples to generate a shortened frame with the next frame to generate the modified block having a length N-Δ

+NR.

4. An apparatus for adjusting an intonation of a sound wherein the sound is specified by a sequence of frames each comprising a set of digital samples, the apparatus comprising:

means for receiving a set of intonation control signals that indicate a pitch adjustment and a duration adjustment to the sound;

buffer that stores the sequence of frames;

intonation control means that generates an intonation adjusted sequence of frames by accessing a block of one or more frames of the sequence of frames from the buffer and by generating a modified block in response to the intonation control signals and by inserting, the modified block into the sequence of frames such that the intonation control frames minimizes a discontinuity between a beginning segment and an ending segment of the block and a pair of adjacent frames in the intonation adjusted sequence of frames;

wherein the intonation control signals indicate a change in a nominal length of a specified frame of the sequence of frames to indicate the pitch adjustment and indicate a change in a number of frames in the sequence of frames to indicate the duration adjustment and,

wherein the intonation control means includes duration shortening means for modifying the block to reduce the number of frames in the sequence of frames wherein the block consists of a pair of sequential frames having lengths NL and NR respectively, the duration shortening means including means for applying a first weighting function to the block emphasizing the beginning segment to generate a first vector and means for applying a second weighting function to the block emphasizing the ending segment to generate a second vector and means for combining the first vector with the second vector to generate the modified block having the length NL or the length NR.

5. An apparatus for adjusting an intonation of a sound wherein the sound is specified by a sequence of frames each comprising a set of digital samples, the apparatus comprising:

means for receiving a set of intonation control signals that indicate a pitch adjustment and a duration adjustment to the sound;

buffer that stores the sequence of frames;

intonation control means that generates an intonation adjusted sequence of frames by accessing a block of one or more frames of the sequence of frames from the buffer and by generating a modified block in response to the intonation control signals and by inserting the modified block into the sequence of frames such that the intonation control frames minimizes a discontinuity between a beginning segment and an ending segment of the block and a pair of adjacent frames in the intonation adjusted sequence of frames;

wherein the intonation control signals indicate a change in a nominal length of a specified frame of the sequence of frames to indicate the pitch adjustment and indicate a change in a number of frames in the sequence of frames to indicate the duration adjustment and,

wherein the intonation control means includes duration lengthening means for modifying the block to increase the number of frames in the sequence of frames wherein the block consists of a pair of left and right sequential frames having lengths NL and NR respectively, the duration lengthening means including means for applying a first weighting function to the block emphasizing the beginning segment to generate a first vector and means for applying a second weighting function to the block emphasizing the ending segment to generate a second vector and means for combining the first vector with the second vector to generate a new frame and means for concatenating the left frame, the new frame, and the right frame to generate the modified block.