# US 2003/0204401 A1 · Low bandwidth speech communication

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2003/0204401 A1
- Document ID: US20030204401A1
- Status: Published application
- Kind: A1
- Application number: 10/128,929
- Filed: 2002-04-24
- Published: 2003-10-30
- Earliest claimed: 2002-04-24
- Assignees: Motorola, Inc.
- Inventors: Thomas Michael Tirpak; Weimin Xiao
- Web page: https://patentgrep.com/patent/US20030204401A1

## CPC

- G10L 19/0018: {Speech coding using phonetic or linguistical decoding of the source; Reconstruction using text-to-speech synthesis}
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

A voice coding and decoding system 300 and method uses a personal phoneme table (320, 344) associated with a voice signature identifier (348) to permit encoding of true sounding voice by personalizing the phoneme table used for encoding and decoding. A default phoneme table (364) is used for encoding and decoding until a personal phoneme table (320, 344) is constructed. A MIDI decoder (360) is used to create the reconstructed speech from a string of phoneme identifiers transmitted from the sending side (302) to the receiving side (304).

## Claims

### Claim 1

A method of speech coding, comprising:
decomposing speech signals into a plurality of phonemes;
assigning a phoneme identifier to each of the plurality of phonemes;
sending an output coded representation of the speech to a decoder, the coded representation suitable for decoding by a decoder by:
transmitting a representation of the plurality of phonemes and their associated identifiers to the decoder for use as a personal phoneme table; and
sending a string of phonemes identifiers to the decoder for decoding by looking up the phoneme in the personal phoneme table.

### Claim 2 (depends on 1)

The method in accordance with claim 1, further comprising:
generating phoneme timing data for each phoneme to indicate the duration of the phoneme; and
transmitting the phoneme timing data for each phoneme.

### Claim 3 (depends on 2)

The method in accordance with claim 2, wherein the timing data are represented by eight bits of digital information specifying the phoneme duration in milliseconds.

### Claim 4 (depends on 1)

The method in accordance with claim 1, further comprising:
identifying dynamic voice attributes associated with the phonemes; and
transmitting a plurality of dynamic voice attribute identifiers associated with the phonemes.

### Claim 5 (depends on 4)

The method in accordance with claim 4, wherein the dynamic voice attribute identifiers are encoded as a sixteen bit digital code.

### Claim 6 (depends on 1)

The method in accordance with claim 1, further comprising:
generating a voice signature identifier from the voice signal; and
transmitting the voice signature identifier.

### Claim 7 (depends on 1)

The method in accordance with claim 1, wherein the phoneme identifiers are encoded as an eight bit digital code.

### Claim 8

A method of speech coding, comprising:
providing a phoneme table containing a plurality of indexed default phonemes;
decomposing speech signals into a plurality of decomposed phonemes; and
substituting the decomposed phonemes for certain of the default indexed phonemes to create a personalized phoneme table.

### Claim 9 (depends on 8)

The method according to claim 8, further comprising transmitting data from the personalized phoneme table from a sending side to a receiving side for use at the receiving side in decoding speech transmitted as phoneme identifiers that index phonemes in the personalized phoneme table.

### Claim 10

A method of speech coding, comprising:
decomposing speech signals into a plurality of phonemes;
assigning a phoneme identifier to each of the plurality of phonemes;
generating phoneme timing data for each phoneme to indicate the duration of the phoneme;
identifying dynamic voice attributes associated with the phonemes;
generating a voice signature identifier from the voice signal; sending an output coded representation of the speech to a decoder, the coded representation suitable for decoding by a decoder by:
transmitting the voice signature identifier;
transmitting a representation of the plurality of phonemes and their associated identifiers to the decoder for use as a personal phoneme table;
sending a string of phonemes identifiers to the decoder for decoding by looking up the phoneme in the personal phoneme table;
transmitting the phoneme timing data for each phoneme; and
transmitting a plurality of dynamic voice attribute identifiers associated with the phonemes.

### Claim 11

A method of decoding speech, comprising:
receiving a string of phoneme identifiers; and
decoding the string of phoneme identifiers using a selected phoneme table, wherein the selected phoneme table is selected from one of a default phoneme table and a personalized phoneme table.

### Claim 12 (depends on 11)

The method in accordance with claim 11, wherein the phoneme identifiers are encoded as an eight bit digital code.

### Claim 13 (depends on 11)

The method according to claim 11, further comprising:
receiving a voice identifier; and
retrieving a stored personalized phoneme table identified by the voice identifier as the selected phoneme table.

### Claim 14 (depends on 11)

The method according to claim 11, further comprising:
receiving the personalized phoneme table; and
wherein the received personalized phoneme table comprises the selected phoneme table.

### Claim 15 (depends on 11)

The method according to claim 11, further comprising:
receiving a voice identifier; and
associating the voice identifier with the personalized phoneme table.

### Claim 16 (depends on 11)

The method according to claim 11, wherein the selected phoneme table is selected as the personalized phoneme table; and
wherein if a phoneme is missing from the personalized phoneme table, a phoneme is selected from the default phoneme table.

### Claim 17 (depends on 11)

The method according to claim 11, wherein the decoding comprises processing the string of phoneme identifiers using a MIDI processor.

### Claim 18 (depends on 11)

The method according to claim 11, further comprising:
receiving phoneme timing data specifying a time duration for each phoneme; and
reconstructing the phoneme using the timing data to determine the time duration for the phoneme.

### Claim 19 (depends on 18)

The method in accordance with claim 18, wherein the timing data are represented by eight bits of digital information specifying the phoneme duration in milliseconds.

### Claim 20 (depends on 11)

The method according to claim 11, further comprising:
receiving a plurality of dynamic voice attribute identifiers with one associated with each phoneme; and
reconstructing each phoneme using the dynamic voice attribute associated therewith to specify voice attributes for the phoneme.

### Claim 21 (depends on 20)

The method in accordance with claim 20, wherein the dynamic voice attribute identifiers are encoded as a sixteen bit digital code.

### Claim 22

A method of decoding speech, comprising:
receiving a voice identifier;
receiving a string of phoneme identifiers;
receiving phoneme timing data specifying a time duration for each phoneme;
receiving a plurality of dynamic voice attribute identifiers with one associated with each phoneme;
decoding the string of phoneme identifiers using MIDI processor to process the phonemes using a selected phoneme table;
wherein the selected phoneme table is selected from at least one of a default phoneme table, a personalized phoneme table identified by the voice identifier and retrieved from memory, and a phoneme table constructed upon receipt of personalized phoneme data and associated with the voice identifier;
wherein if a phoneme is missing from the personalized phoneme table, a phoneme is selected from the default phoneme table; and
wherein the decoding comprises reconstructing the phoneme using the timing data to determine the time duration for the phoneme and using the dynamic voice attribute associated with the phoneme to specify voice attributes for the phoneme.

### Claim 23

A method of constructing a personalized phoneme table for speech transmission using a phoneme based speech communication system, comprising:
initializing a personalized phoneme table with a set of default values;
decomposing a speech signal into a plurality of phonemes; and
replacing certain of the default values with the plurality of phonemes.

### Claim 24 (depends on 23)

The method in accordance with claim 23, further comprising transmitting data from the personalized phoneme table from a sender side to a receiver side of the phoneme based speech communication system.

### Claim 25 (depends on 24)

The method in accordance with claim 24, further comprising decoding a string of phoneme identifiers at the receiver side into speech using the personalized phoneme table.
