Program to record speech audio into RAM and then play it back, moving Billy Bass's mouth in sync with the speech.

Dependencies:   mbed

Remember Big Mouth Billy Bass?

I've made a simple demo program for him using the Freescale FRDM-KL25Z board. I've hooked up the digital I/O to his motor driver transistors and pushbutton switch.

This program records 1.8 seconds of speech audio from ADC input when the pushbutton is pressed, then plays the audio back with Billy Bass's mouth controlled so that it opens during vowel sounds.

The ADC input is driven from a microphone and preamplifier, via a capacitor and into a resistor divider connected to the +3.3V supply pin to provide mid-range biasing for the ADC signals.

The DAC output is connected to his audio amplifier input (to the trace that was connected to pin 10 of the controller IC). I had to provide a DC bias using the DAC to get the single transistor amplifier biased into proper operation.

For more on the method of vowel recognition, please see the paper: http://www.mirlab.org/conference_papers/International_Conference/ICASSP%201999/PDF/AUTHOR/IC991957.PDF

Y. Nishida, Y. Nakadai, Y. Suzuki, T. Sakurai, T. Kurokawa, and H. Sato. 1999.

Voice recognition focusing on vowel strings on a fixed-point 20-MIPS DSP board.

In Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01 (ICASSP '99), Vol. 1. IEEE Computer Society, Washington, DC, USA, 137-140. DOI=10.1109/ICASSP.1999.758081 http://dx.doi.org/10.1109/ICASSP.1999.758081

main.cpp

Committer:
bikeNomad
Date:
2013-05-14
Revision:
2:5bcd2f55a294
Parent:
1:2fa375aacece
Child:
3:c04d8d0493f4

File content as of revision 2:5bcd2f55a294:

#include "mbed.h"
#include "FastAnalogIn.h"
using namespace NK;

// Power:
// Power GND  J9/14
// Vin (6V)   J9/16

// Digital:
DigitalOut tail(PTA13);     // J3/2
DigitalOut mouth(PTC12);    // J3/1
DigitalOut head(PTC13);     // J3/3
DigitalIn pushbutton(PTD5); // J3/4

PwmOut redLED(LED_RED);
PwmOut greenLED(LED_GREEN);
PwmOut blueLED(LED_BLUE);

// Analog:
// GND   J3/14
// VrefH J3/16
FastAnalogIn microphone(PTB0);  // J10/2
AnalogOut speaker(PTE30);   // J10/11

// Communications:
// Serial uart1(PTC4, PTC3);
Serial pc(USBTX, USBRX);

const unsigned SAMPLE_RATE_HZ  = 7889;
const unsigned SAMPLE_PERIOD_US     = (1000000U / SAMPLE_RATE_HZ);
const unsigned SAMPLE_BUFFER_SIZE = 9000;

Ticker sampleTicker;
Timer timer;

uint8_t sampleBuffer[SAMPLE_BUFFER_SIZE];      // 1 second buffer
uint8_t * volatile nextSample;
unsigned volatile samplesRemaining;

extern "C"
void ADC0_IRQHandler(void)
{
    if (samplesRemaining) {
        *nextSample++ = microphone.read_u16_nowait() >> 8;
        microphone.start_read();
        samplesRemaining--;
    } else {
        microphone.disable_interrupt();
        microphone.abort_read();
        timer.stop();
    }
}

void playAudioSample()
{
    if (samplesRemaining) {
        speaker.write_u16(*nextSample++ << 8);
        samplesRemaining--;
    } else {
        sampleTicker.detach();
        timer.stop();
    }
}

void resetSampleBuffer()
{
    nextSample = sampleBuffer;
    samplesRemaining = SAMPLE_BUFFER_SIZE;
}

void recordAudio()
{
    pc.printf("Recording %d samples... ", SAMPLE_BUFFER_SIZE);
    blueLED = 0.0;

    resetSampleBuffer();
    timer.start();
    microphone.enable_interrupt();
    microphone.start_read();

    while (samplesRemaining) {
        wait_us(50000);
        blueLED.write(1.0 - (1.0 * samplesRemaining / SAMPLE_BUFFER_SIZE));
    }

    float elapsed = timer.read();
    pc.printf("Done. %u samples in %f usec = %f samples/sec\r\n", SAMPLE_BUFFER_SIZE, elapsed * 1.0e6, SAMPLE_BUFFER_SIZE / elapsed);
}

void playAudio(float duration)
{
    pc.printf("Playing %d samples... ", SAMPLE_BUFFER_SIZE);
    greenLED = 0.0;
    resetSampleBuffer();
    timer.reset();
    timer.start();
    sampleTicker.attach(&playAudioSample, duration/SAMPLE_BUFFER_SIZE);
    while (samplesRemaining) {
        wait_us(50000);
        greenLED.write(1.0 - (1.0 *  samplesRemaining / SAMPLE_BUFFER_SIZE));
    }
    float elapsed = timer.read();
    pc.printf("Done. %u samples in %f usec = %f samples/sec", SAMPLE_BUFFER_SIZE, elapsed * 1.0e6, SAMPLE_BUFFER_SIZE / elapsed);
    pc.printf(" (Rate %#+0.2f%%)\r\n", (duration-elapsed)*100/duration);
}

int main()
{
    pc.baud(115200);
    pc.printf("\r\n\r\nSample buffer = %u samples; rate = %u Hz; period = %u usec\r\n", SAMPLE_BUFFER_SIZE, SAMPLE_RATE_HZ, SAMPLE_PERIOD_US);
    redLED = 1.0;
    greenLED = 1.0;
    blueLED = 1.0;

    recordAudio();

    playAudio(timer.read());
}