How to detect speech start on iOS Speech API
I would recommend low-pass filtering the power signal using AVAudioRecorder
and a NSTimer
for callback. This way you'll be able to detect when a certain threshold is reached in the audio recorder readings, and the low-pass filtering will help mitigating the noise.
In the .h file:
#import <UIKit/UIKit.h>
#import <AVFoundation/AVFoundation.h>
#import <CoreAudio/CoreAudioTypes.h>
@interface ViewController : UIViewController{
AVAudioRecorder *recorder;
NSTimer *levelTimer;
double lowPassResults;
}
- (void)levelTimerCallback:(NSTimer *)timer;
@end
In the .m file:
#import "ViewController.h"
@interface ViewController ()
@end
@implementation ViewController
- (void)viewDidLoad {
[super viewDidLoad];
// AVAudioSession already set in your code, so no need for these 2 lines.
[[AVAudioSession sharedInstance] setCategory:AVAudioSessionCategoryPlayAndRecord error:nil];
[[AVAudioSession sharedInstance] setActive:YES error:nil];
NSURL *url = [NSURL fileURLWithPath:@"/dev/null"];
NSDictionary *settings = [NSDictionary dictionaryWithObjectsAndKeys:
[NSNumber numberWithFloat: 44100.0], AVSampleRateKey,
[NSNumber numberWithInt: kAudioFormatAppleLossless], AVFormatIDKey,
[NSNumber numberWithInt: 1], AVNumberOfChannelsKey,
[NSNumber numberWithInt: AVAudioQualityMax], AVEncoderAudioQualityKey,
nil];
NSError *error;
lowPassResults = 0;
recorder = [[AVAudioRecorder alloc] initWithURL:url settings:settings error:&error];
if (recorder) {
[recorder prepareToRecord];
recorder.meteringEnabled = YES;
[recorder record];
levelTimer = [NSTimer scheduledTimerWithTimeInterval: 0.05 target: self selector: @selector(levelTimerCallback:) userInfo: nil repeats: YES];
} else
NSLog(@"%@", [error description]);
}
- (void)levelTimerCallback:(NSTimer *)timer {
[recorder updateMeters];
const double ALPHA = 0.05;
double peakPowerForChannel = pow(10, (0.05 * [recorder peakPowerForChannel:0]));
lowPassResults = ALPHA * peakPowerForChannel + (1.0 - ALPHA) * lowPassResults;
NSLog(@"lowPassResults: %f",lowPassResults);
// Use here a threshold value to stablish if there is silence or speech
if (lowPassResults < 0.1) {
NSLog(@"Silence");
} else if(lowPassResults > 0.5){
NSLog(@"Speech");
}
}
- (void)didReceiveMemoryWarning {
[super didReceiveMemoryWarning];
// Dispose of any resources that can be recreated.
}
@end
This is the code we ended up with that works.
The key thing was to installTapOnBus() and then the magic code to detect the volume,
float volume = fabsf(*buffer.floatChannelData[0]);
-(void) doActualRecording {
NSLog(@"doActualRecording");
@try {
//if (!recording) {
if (audioEngine != NULL) {
[audioEngine stop];
[speechTask cancel];
AVAudioInputNode* inputNode = [audioEngine inputNode];
[inputNode removeTapOnBus: 0];
}
recording = YES;
micButton.selected = YES;
//NSLog(@"Starting recording... SFSpeechRecognizer Available? %d", [speechRecognizer isAvailable]);
NSError * outError;
//NSLog(@"AUDIO SESSION CATEGORY0: %@", [[AVAudioSession sharedInstance] category]);
AVAudioSession* audioSession = [AVAudioSession sharedInstance];
[audioSession setCategory: AVAudioSessionCategoryPlayAndRecord withOptions:AVAudioSessionCategoryOptionDefaultToSpeaker error:&outError];
[audioSession setMode: AVAudioSessionModeMeasurement error:&outError];
[audioSession setActive: true withOptions: AVAudioSessionSetActiveOptionNotifyOthersOnDeactivation error:&outError];
SFSpeechAudioBufferRecognitionRequest* speechRequest = [[SFSpeechAudioBufferRecognitionRequest alloc] init];
//NSLog(@"AUDIO SESSION CATEGORY1: %@", [[AVAudioSession sharedInstance] category]);
if (speechRequest == nil) {
NSLog(@"Unable to create SFSpeechAudioBufferRecognitionRequest.");
return;
}
speechDetectionSamples = 0;
// This some how fixes a crash on iPhone 7
// Seems like a bug in iOS ARC/lack of gc
AVAudioEngine* temp = audioEngine;
audioEngine = [[AVAudioEngine alloc] init];
AVAudioInputNode* inputNode = [audioEngine inputNode];
speechRequest.shouldReportPartialResults = true;
// iOS speech does not detect end of speech, so must track silence.
lastSpeechDetected = -1;
speechTask = [speechRecognizer recognitionTaskWithRequest: speechRequest delegate: self];
[inputNode installTapOnBus:0 bufferSize: 4096 format: [inputNode outputFormatForBus:0] block:^(AVAudioPCMBuffer* buffer, AVAudioTime* when) {
@try {
long long millis = [[NSDate date] timeIntervalSince1970] * 1000;
if (lastSpeechDetected != -1 && ((millis - lastSpeechDetected) > 1000)) {
lastSpeechDetected = -1;
[speechTask finish];
return;
}
[speechRequest appendAudioPCMBuffer: buffer];
//Calculate volume level
if ([buffer floatChannelData] != nil) {
float volume = fabsf(*buffer.floatChannelData[0]);
if (volume >= speechDetectionThreshold) {
speechDetectionSamples++;
if (speechDetectionSamples >= speechDetectionSamplesNeeded) {
//Need to change mic button image in main thread
[[NSOperationQueue mainQueue] addOperationWithBlock:^ {
[micButton setImage: [UIImage imageNamed: @"micRecording"] forState: UIControlStateSelected];
}];
}
} else {
speechDetectionSamples = 0;
}
}
}
@catch (NSException * e) {
NSLog(@"Exception: %@", e);
}
}];
[audioEngine prepare];
[audioEngine startAndReturnError: &outError];
NSLog(@"Error %@", outError);
//}
}
@catch (NSException * e) {
NSLog(@"Exception: %@", e);
}
}