# US 6,732,073 B1 · Spectral enhancement of acoustic signals to provide improved recognition of speech

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

- Number: US 6,732,073 B1
- Document ID: US6732073B1
- Status: Granted
- Kind: B1
- Application number: 09/726,545
- Filed: 2000-09-07
- Granted: 2004-05-04
- Earliest claimed: 1999-09-10
- Assignees: Wisconsin Alumni Research Foundation
- Inventors: Keith R. Kluender; Rick L. Jenison
- Web page: https://patentgrep.com/patent/US6732073B1

## CPC

- G10L 15/02: Feature extraction for speech recognition; Selection of recognition unit
- H04R 25/505: {using digital signal processing}
- H04R 25/356: {Amplitude, e.g. amplitude shift or compression}
- H04R 2225/43: Signal processing in hearing aids to enhance the speech intelligibility
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- H04R: LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; ELECTRIC HEARING AIDS; PUBLIC ADDRESS SYSTEMS (producing sounds with frequency not determined by supply frequency G10K)

## Abstract

A method and apparatus for enhancing an auditory signal to make sounds, particularly speech sounds, more distinguishable. An input auditory signal is divided into a plurality of spectral channels. An output gain for each channel is derived based on the time varying history of the energy in the channel and, preferably, the time varying history of energy in neighboring channels. The magnitude of the output gain for each channel thus derived is preferably inversely related to the history of energy in the channel. The output gain derived for each channel is applied to the channel to form a plurality of modified spectral channel signals. The plurality of modified spectral channel signals are combined to form an enhanced output auditory signal. The present invention is particularly applicable to electronic hearing aid devices, speech recognition systems, and the like.

## Claims

### Claim 1

A method for enhancing an auditory signal, comprising the steps of:
(a) dividing an input auditory signal into a plurality of spectral channels;
(b) determining an output gain for each channel based on the time varying history of energy in the channel and wherein the magnitude of the output gain for each channel is inversely related to the history of energy in the channel;
(c) applying the output gain for each channel to the channel to form a plurality of modified spectral channel signals; and
(d) combining the plurality of modified spectral channel signals to form an enhanced output auditory signal.

### Claim 2 (depends on 1)

The method of claim 1 wherein the step of dividing the input auditory signal into a plurality of spectral channels includes the step of applying the input auditory signal to a bank of gammatone filters.

### Claim 3 (depends on 1)

The method of claim 1 wherein the step of dividing the input auditory signal into a plurality of spectral channels includes the step of applying the input auditory signal to a quadrature mirror filter bank.

### Claim 4 (depends on 1)

The method of claim 1 wherein the step of determining the output gain for each channel includes the steps of determining a weighted energy history for each channel based on the time varying history of the energy in the channel, converting the weighted energy history into an RMS history weighting value between 0 and 1, and subtracting the RMS history weighting value from unity to determine the output gain for the channel.

### Claim 5 (depends on 4)

The method of claim 4 wherein the step of determining the weighted energy history for each channel includes the step of determining the weighted energy history for each channel such that the energy in the channel in more recent time past is weighted more heavily than energy in the channel in the present and in the more distant past.

### Claim 6

A method for enhancing an auditory signal, comprising the steps of:
(a) dividing an input auditory signal into a plurality of spectral channels;
(b) determining an output gain for each channel based on the time varying history of energy in the channel and the time varying history of energy in neighboring channels;
(c) applying the output gain for each channel to the channel to form a plurality of modified spectral channel signals; and
(d) combining the plurality of modified spectral channel signals to form an enhanced output auditory signal.

### Claim 7 (depends on 6)

The method of claim 6 wherein the step of dividing the input auditory signal into a plurality of spectral channels includes the step of applying the input auditory signal to a bank of gammatone filters.

### Claim 8 (depends on 6)

The method of claim 6 wherein the step of dividing the input auditory signal into a plurality of spectral channels includes the step of applying the input auditory signal to a quadrature mirror filter bank.

### Claim 9 (depends on 6)

The method of claim 6 wherein the step of determining the output gain for each channel includes the steps of determining a weighted energy history for each channel based on the time varying history of the energy in the channel, converting the weighted energy history into an RMS history weighting value, and subtracting the ratio of the RMS history weighting value in the channel to a sum of RMS history weighting values in neighboring channels from unity to determine the output gain for the channel.

### Claim 10 (depends on 9)

The method of claim 9 wherein the step of determining the weighted energy history for each channel includes the step of determining the weighted energy history for each channel such that the energy in the channel in more recent time past is weighted more heavily than energy in the channel in the present and in the more distant past.

### Claim 11

A system for enhancing an auditory signal, comprising:
(a) a microphone for receiving an auditory signal and providing an analog electrical signal in response thereto;
(b) an analog-to-digital converter connected to the microphone for converting the analog electrical signal into a digital input signal;
(c) a signal processor system connected to the analog-to-digital converter for receiving the digital input signal and programmed to divide the input signal into a plurality of spectral channels, determine an output gain for each channel based on the time varying history of energy in the channel and wherein the magnitude of the output gain for each channel is inversely related to the history of energy in the channel, apply the output gain for each channel to the channel to form a plurality of modified spectral channel signals, and combine the plurality of modified spectral channel signals to form an enhanced digital output signal.

### Claim 12 (depends on 11)

The system of claim 11 comprising additionally:
(a) an digital-to-analog converter connected to the signal processor system for converting the digital output signal to an analog electrical output signal; and
(b) a speaker connected to the digital-to-analog converter for converting the analog electrical signal into an auditory signal.

### Claim 13 (depends on 12)

The system of claim 12 wherein the microphone, analog-to-digital converter, signal processor system, digital-to-analog converter, and speaker are contained in a hearing aid device.

### Claim 14 (depends on 11)

The system of claim 11 comprising additionally a speech recognition system connected to the signal processor system to receive the digital output signal therefrom.

### Claim 15

A system for enhancing an auditory signal, comprising:
(a) a microphone for receiving an auditory signal and providing an analog electrical signal in response thereto;
(b) an analog-to-digital converter connected to the microphone for converting the analog electrical signal into a digital input signal;
(c) a signal processor system connected to the analog-to-digital converter for receiving the digital input signal and programmed to divide the input signal into a plurality of spectral channels, determine an output gain for each channel based on the time varying history of energy in the channel and the time varying history of energy in neighboring channels, apply the output gain for each channel to the channel to form a plurality of modified spectral channel signals, and combine the plurality of modified spectral channel signals to form an enhanced digital output signal.

### Claim 16 (depends on 15)

The system of claim 15 comprising additionally:
(a) an digital-to-analog converter connected to the signal processor system for converting the digital output signal to an analog electrical output signal; and
(b) a speaker connected to the digital-to-analog converter for converting the analog electrical signal into an auditory signal.

### Claim 17 (depends on 16)

The system of claim 16 wherein the microphone, analog-to-digital converter, signal processor system, digital-to-analog converter, and speaker are contained in a hearing aid device.

### Claim 18 (depends on 15)

The system of claim 15 comprising additionally a speech recognition system connected to the signal processor system to receive the digital output signal therefrom.
