# US 2014/0195227 A1 · System and method for acoustic transformation

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

- Number: US 2014/0195227 A1
- Document ID: US20140195227A1
- Status: Published application
- Kind: A1
- Application number: 14/153,942
- Filed: 2014-01-13
- Published: 2014-07-10
- Earliest claimed: 2011-07-25
- Inventors: Frank RUDZICZ; Graeme John HIRST; Pascal Hubert Henri Marie VAN LIESHOUT; Graham Fraser SHEIN; Gerald Bradley PENN
- Web page: https://patentgrep.com/patent/US20140195227A1

## CPC

- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10H 1/366: {with means for modifying or correcting the external signal, e.g. pitch correction, reverberation, changing a singer's voice}
- G10L 21/003: Changing voice quality, e.g. pitch or formants
- G10H 2250/541: Details of musical waveform synthesis, i.e. audio waveshape processing from individual wavetable samples, independently of their origin or of the sound they represent
- G10L 21/0364: for improving intelligibility
- G10L 25/60: for measuring the quality of voice signals
- G10L 2021/0135: {Voice conversion or morphing}
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10H: ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE

## Abstract

An acoustic transformation system and method. A specific embodiment is the transformation of acoustic speech signals produced by speakers with speech disabilities in order to make those utterances more intelligible to typical listeners. These modifications include the correction of tempo or rhythm, the adjustment of formant frequencies in sonorants, the removal of adjustment of aberrant voicing, the deletion of phoneme insertion errors, and the replacement of erroneously dropped phonemes. These methods may also be applied to general correction of musical or acoustic sequences.

## Claims

### Claim 1

A system for transforming an acoustic signal comprising an acoustic transformation engine operable to apply one or more transformations to the acoustic signal in accordance with one or more transformation rules configured to determine the correctness of each of one or more temporal segments of the acoustic signal.

### Claim 2 (depends on 1)

The system of claim 1, wherein the acoustic transformation engine is operable to morph or transform a segment determined to be incorrect.

### Claim 3 (depends on 1)

The system of claim 1, wherein the acoustic transformation engine is operable to replace a segment determined to be incorrect with a sample sound.

### Claim 4 (depends on 1)

The system of claim 1, wherein the acoustic transformation engine is operable to delete a segment determined to be incorrect.

### Claim 5 (depends on 1)

The system of claim 1, wherein the acoustic transformation engine is operable to insert a sample sound or synthesize a sound between two segments determined to be incorrectly adjacent.

### Claim 6 (depends on 1)

The system of claim 1, wherein the transformations comprise one or more of filtering, splicing, time transforming and frequency transforming.

### Claim 7 (depends on 1)

The system of claim 1, wherein the transformation rules relate to empirical findings of improper acoustic signals.

### Claim 8 (depends on 1)

The system of claim 1, wherein the transformation rules apply automated or semi-automated annotation of the acoustic signal to identify the segments.

### Claim 9 (depends on 1)

The system of claim 1, wherein applying the transformations comprises obtaining a reference signal or reference parameters from an acoustic sample database.

### Claim 10 (depends on 1)

The system of claim 1, wherein the acoustic transformation engine applies the transformations in parallel and combines transformed acoustic signals to produce a transformed signal.

### Claim 11

A method for transforming an acoustic signal comprising:
(a) configuring one or more transformation rules to determine the correctness of each of one or more temporal segments of the acoustic signal; and
(b) applying, by an acoustic transformation engine, one or more transformations to the acoustic signal in accordance with the one or more transformation rules.

### Claim 12 (depends on 11)

The method of claim 11, further comprising morphing or transforming a segment determined to be incorrect.

### Claim 13 (depends on 11)

The method of claim 11, further comprising replacing a segment determined to be incorrect with a sample sound.

### Claim 14 (depends on 11)

The method of claim 11, further comprising deleting a segment determined to be incorrect.

### Claim 15 (depends on 11)

The method of claim 11, further comprising inserting a sample sound or synthesizing a sound between two segments determined to be incorrectly adjacent.

### Claim 16 (depends on 11)

The method of claim 11, wherein the transformations comprise one or more of filtering, splicing, time transforming and frequency transforming.

### Claim 17 (depends on 11)

The method of claim 11, wherein the transformation rules relate to empirical findings of improper acoustic signals.

### Claim 18 (depends on 11)

The method of claim 11, wherein the transformation rules apply automated or semi-automated annotation of the acoustic signal to identify the segments.

### Claim 19 (depends on 11)

The method of claim 11, wherein applying the transformations comprises obtaining a reference signal or reference parameters from an acoustic sample database.

### Claim 20 (depends on 11)

The method of claim 11, further comprising applying the transformations in parallel and combining transformed acoustic signals to produce a transformed signal.