1/*
2 *  Copyright (c) 2012 The WebRTC project authors. All Rights Reserved.
3 *
4 *  Use of this source code is governed by a BSD-style license
5 *  that can be found in the LICENSE file in the root of the source
6 *  tree. An additional intellectual property rights grant can be found
7 *  in the file PATENTS.  All contributing project authors may
8 *  be found in the AUTHORS file in the root of the source tree.
9 */
10
11
12/*
13 * This header file includes the VAD API calls. Specific function calls are given below.
14 */
15
16#ifndef WEBRTC_COMMON_AUDIO_VAD_INCLUDE_WEBRTC_VAD_H_  // NOLINT
17#define WEBRTC_COMMON_AUDIO_VAD_INCLUDE_WEBRTC_VAD_H_
18
19#include "webrtc/typedefs.h"
20
21typedef struct WebRtcVadInst VadInst;
22
23#ifdef __cplusplus
24extern "C" {
25#endif
26
27// Creates an instance to the VAD structure.
28//
29// - handle [o] : Pointer to the VAD instance that should be created.
30//
31// returns      : 0 - (OK), -1 - (Error)
32int WebRtcVad_Create(VadInst** handle);
33
34// Frees the dynamic memory of a specified VAD instance.
35//
36// - handle [i] : Pointer to VAD instance that should be freed.
37void WebRtcVad_Free(VadInst* handle);
38
39// Initializes a VAD instance.
40//
41// - handle [i/o] : Instance that should be initialized.
42//
43// returns        : 0 - (OK),
44//                 -1 - (NULL pointer or Default mode could not be set).
45int WebRtcVad_Init(VadInst* handle);
46
47// Sets the VAD operating mode. A more aggressive (higher mode) VAD is more
48// restrictive in reporting speech. Put in other words the probability of being
49// speech when the VAD returns 1 is increased with increasing mode. As a
50// consequence also the missed detection rate goes up.
51//
52// - handle [i/o] : VAD instance.
53// - mode   [i]   : Aggressiveness mode (0, 1, 2, or 3).
54//
55// returns        : 0 - (OK),
56//                 -1 - (NULL pointer, mode could not be set or the VAD instance
57//                       has not been initialized).
58int WebRtcVad_set_mode(VadInst* handle, int mode);
59
60// Calculates a VAD decision for the |audio_frame|. For valid sampling rates
61// frame lengths, see the description of WebRtcVad_ValidRatesAndFrameLengths().
62//
63// - handle       [i/o] : VAD Instance. Needs to be initialized by
64//                        WebRtcVad_Init() before call.
65// - fs           [i]   : Sampling frequency (Hz): 8000, 16000, or 32000
66// - audio_frame  [i]   : Audio frame buffer.
67// - frame_length [i]   : Length of audio frame buffer in number of samples.
68//
69// returns              : 1 - (Active Voice),
70//                        0 - (Non-active Voice),
71//                       -1 - (Error)
72int WebRtcVad_Process(VadInst* handle, int fs, const int16_t* audio_frame,
73                      int frame_length);
74
75// Checks for valid combinations of |rate| and |frame_length|. We support 10,
76// 20 and 30 ms frames and the rates 8000, 16000 and 32000 Hz.
77//
78// - rate         [i] : Sampling frequency (Hz).
79// - frame_length [i] : Speech frame buffer length in number of samples.
80//
81// returns            : 0 - (valid combination), -1 - (invalid combination)
82int WebRtcVad_ValidRateAndFrameLength(int rate, int frame_length);
83
84#ifdef __cplusplus
85}
86#endif
87
88#endif  // WEBRTC_COMMON_AUDIO_VAD_INCLUDE_WEBRTC_VAD_H_  // NOLINT
89