public class AcousticNoiseSuppressor extends Object implements SpeechProcessor
AcousticNoiseSuppressor is a speech pipeline component that implements automatic noise separation and suppression. The denoised frames are written back to the frame buffer in-place. The VAD implementation is based on the webrtc noise suppressor in the Chromium browser. It supports 16-bit PCM samples with a frame rate multiple of 10ms.
This pipeline component supports the following configuration properties:
| Modifier and Type | Field and Description |
|---|---|
static String |
DEFAULT_POLICY
default suppressor policy.
|
| Constructor and Description |
|---|
AcousticNoiseSuppressor(SpeechConfig config)
constructs a new suppressor instance.
|
| Modifier and Type | Method and Description |
|---|---|
void |
close()
destroys the unmanaged ans instance.
|
void |
process(SpeechContext context,
ByteBuffer frame)
processes a frame of audio.
|
void |
reset()
resets all state internal to the stage.
|
public static final String DEFAULT_POLICY
public AcousticNoiseSuppressor(SpeechConfig config)
config - the pipeline configuration instancepublic void reset()
SpeechProcessorreset in interface SpeechProcessorpublic void close()
close in interface AutoCloseablepublic void process(SpeechContext context, ByteBuffer frame)
process in interface SpeechProcessorcontext - the current speech contextframe - the audio frame to detectCopyright © 2021. All rights reserved.