Can we use speech structure while filming?

I am playing a video using AVPlayerController and thus want to use a voice command to stop the video. So I tried to use speech frames for them, but I am getting com.apple.coreaudio.avfaudio ' error , reason:' prerequisite false: format.sampleRate == hwFormat.sampleRate '

I tried to use category for session on reuse using speech structure

[AVAudioSession setCategory:AVAudioSessionCategoryPlayAndRecord withOptions:AVAudioSessionCategoryOptionMixWithOthers error:&sessionError];

      

        
        
        
      

    

Also it is not possible to get a response in the recognition of TaskWithRequest

Do I need to check the noise reduction algorithm or some other process I need to do. Is it possible? Any help or suggestions would be appreciated.