Audio2Face简介
在元宇宙的热潮下，为了让AI数字人渗透到更多的领域中，FACEGOOD已经将语音驱动口型的算法技术开源，开源地址：
https://github.com/FACEGOOD/FACEGOOD-Audio2Face
该技术可以实时将音频数据转换为驱动数字人面部BlendShape的权重数据，不同于ARKit中的52个BlendShape，它的数量多达116个，我们可以通过对应关系得到相应的数值，对应关系如下：
| ARKit | Voice2Face | | eyeBlinkLeft | eye_blink2_l | | eyeLookDownLeft | eye_lookDown2_l | | eyeLookInLeft | eye_lookRight_l | | eyeLookOutLeft | eye_lookLeft_l | | eyeLookUpLeft | eye_lookUp_l | | eyeSquintLeft | eye_shutTight_l | | eyeWideLeft | max(eye_downLidRaise_l,eye_upLidRaise_l) | | eyeBlinkRight | eye_blink2_r | | eyeLookDownRight | eye_lookDown2_r | | eyeLookInRight | eye_lookRight_r | | eyeLookOutRight | eye_lookLeft_r | | eyeLookUpRight | eye_lookUp_r | | eyeSquintRight | eye_shutTight_r | | eyeWideRight | max(eye_downLidRaise_r,eye_upLidRaise_r) | | jawForward | jaw_thrust_c | | jawLeft | jaw_sideways_l | | jawRight | jaw_sideways_r | | jawOpen | mouth_stretch_c | | mouthClose | mouth_chew_c | | mouthFunnel | max(mouth_funnel_dl,mouth_funnel_dr,mouth_funnel_ul,mouth_funnel_ur) | | mouthPucker | max(mouth_pucker_l,mouth_pucker_r) | | mouthLeft | mouth_sideways_l | | mouthRight | mouth_sideways_r | | mouthSmileLeft | mouth_lipCornerPull_l | | mouthSmileRight | mouth_lipCornerPull_r | | mouthFrownLeft | max(mouth_lipCornerDepress_l,mouth_lipCornerDepressFix_l) | | mouthFrownRight | max(mouth_lipCornerDepress_r,mouth_lipCornerDepressFix_r) | | mouthDimpleLeft | mouth_dimple_l | | mouthDimpleRight | mouth_dimple_r | | mouthStretchLeft | mouth_lipStretch_l | | mouthStretchRight | mouth_lipStretch_r | | mouthRollLower | max(mouth_suck_dl,mouth_suck_dr) | | mouthRollUpper | max(mouth_suck_ul,mouth_suck_ur) | | mouthShrugLower | mouth_chinRaise_d | | mouthShrugUpper | mouth_chinRaise_u | | mouthPressLeft | mouth_press_l | | mouthPressRight | mouth_press_r | | mouthLowerDownLeft | mouth_lowerLipDepress_l | | mouthLowerDownRight | mouth_lowerLipDepress_r | | mouthUpperUpLeft | mouth_upperLipRaise_l | | mouthUpperUpRight | mouth_upperLipRaise_r | | browDownleft | brow_lower_l | | browDownRight | brow_lower_r | | browInnerUp | brow_raise_c | | browOuterUpLeft | brow_raise_l | | browOuterUpRight | brow_raise_r | | cheekPuff | max(cheek_puff_l,cheek_puff_r) | | cheekSquintLeft | cheek_up | | cheekSquintRight | cheek_up | | noseSneerLeft | nose_out_l | | noseSneerRight | nose_out_r | | tongueOut | |
生产的数据结果如下图所示，可见是116个取值范围为-1~1的小数：
这116个数值依次对应下面116个BlendShape名称：
mouth_lipCornerDepressFix_l mouth_lipCornerDepressFix_r mouth_lipCornerPullOpen_l mouth_lipCornerPullOpen_r
可以用过构建python服务，Unity客户端开启麦克风录制音频，将音频数据发送给python服务端，服务端转换为驱动BlendShape的权重数据后，返回给Unity客户端进行驱动。需要注意的是Unity中BlendShape的权重范围并不是[-1,1]，因此需要进行映射。
例如：
private float Remap(float v)
下面是一段测试音频产生的bs权重数据文件，每一行包含116个权重数值，我们拿来进行测试，将其放到StreamingAssets文件夹下。
测试模型：
测试代码：
using System.Collections; using System.Collections.Generic; public class TEST : MonoBehaviour private Coroutine coroutine; private SkinnedMeshRenderer smr; private readonly List<List<float>> valueList = new List<List<float>>(); private IEnumerator Start() smr = GetComponent<SkinnedMeshRenderer>(); string path = Path.Combine(Application.streamingAssetsPath, 'weight.txt'); using (StreamReader streamReader = new StreamReader(path)) while ((content = streamReader.ReadLine()) != null) List<float> list = new List<float>(); content = content.Trim(); string[] splitArray = content.Split(' '); for (int i = 0; i < splitArray.Length; i++) float.TryParse(splitArray[i], out float result); private IEnumerator ExecuteCoroutine() for (int i = 0; i < valueList.Count; i++) List<float> list = valueList[i]; smr.SetBlendShapeWeight(0, Remap(list[49])); //brow_raise_l smr.SetBlendShapeWeight(1, Remap(list[60])); //brow_raise_r smr.SetBlendShapeWeight(2, Remap(list[25])); //eye_shutTight_l smr.SetBlendShapeWeight(3, Remap(list[26])); //eye_shutTight_r smr.SetBlendShapeWeight(4, Remap(list[87])); //eye_lookRight_l smr.SetBlendShapeWeight(5, Remap(list[86])); //eye_lookLeft_l smr.SetBlendShapeWeight(6, Remap(list[92])); //eye_lookRight_r smr.SetBlendShapeWeight(7, Remap(list[91])); //eye_lookLeft_r smr.SetBlendShapeWeight(8, Remap(list[88])); //eye_lookUp_l smr.SetBlendShapeWeight(9, Remap(list[94])); //eye_lookUp_r smr.SetBlendShapeWeight(10, Remap(list[85])); //eye_lookDown2_l smr.SetBlendShapeWeight(11, Remap(list[90])); //eye_lookDown2_r smr.SetBlendShapeWeight(12, Mathf.Max(Remap(list[71]), Remap(list[82]))); //cheek_pull_l cheek_pull_r smr.SetBlendShapeWeight(13, Remap(list[18])); //cheek_UP smr.SetBlendShapeWeight(14, Remap(list[18])); //cheek_UP smr.SetBlendShapeWeight(15, Remap(list[6])); //nose_out_l smr.SetBlendShapeWeight(16, Remap(list[7])); //nose_out_r smr.SetBlendShapeWeight(17, Remap(list[70])); //mouth_sideways_l smr.SetBlendShapeWeight(18, Remap(list[72])); //mouth_sideways_r smr.SetBlendShapeWeight(19, Mathf.Max(Remap(list[67]), Remap(list[68]))); //mouth_pucker_l mouth_pucker_2 smr.SetBlendShapeWeight(20, Mathf.Max(Remap(list[41]), Remap(list[42]), Remap(list[43]), Remap(list[44]))); //mouth_funnel_dl dr ul ur smr.SetBlendShapeWeight(21, Remap(list[52])); //mouth_lipCornerPull_l smr.SetBlendShapeWeight(22, Remap(list[53])); //mouth_lipCornerPull_r smr.SetBlendShapeWeight(23, Mathf.Max(Remap(list[47]), Remap(list[45]))); //mouth_lipCornerDepress_l mouth_lipCornerDepressFix_l smr.SetBlendShapeWeight(24, Mathf.Max(Remap(list[48]), Remap(list[46]))); //mouth_lipCornerDepress_r mouth_lipCornerDepressFix_r smr.SetBlendShapeWeight(25, Remap(list[39])); //mouth_dimple_l smr.SetBlendShapeWeight(26, Remap(list[40])); //mouth_dimple_r smr.SetBlendShapeWeight(27, Remap(list[65])); //mouth_press_l smr.SetBlendShapeWeight(28, Remap(list[66])); //mouth_press_r smr.SetBlendShapeWeight(29, Remap(list[36])); //mouth_chinRaise_d smr.SetBlendShapeWeight(30, Remap(list[37])); //mouth_chinRaise_u smr.SetBlendShapeWeight(31, Remap(list[56])); //mouth_lipStretch_l smr.SetBlendShapeWeight(32, Remap(list[57])); //mouth_lipStretch_r smr.SetBlendShapeWeight(33, Remap(list[78])); //mouth_upperLipRaise_l smr.SetBlendShapeWeight(34, Remap(list[79])); //mouth_upperLipRaise_r smr.SetBlendShapeWeight(35, Remap(list[58])); //mouth_lowerLipDepress_l smr.SetBlendShapeWeight(36, Remap(list[59])); //mouth_lowerLipDepress_r smr.SetBlendShapeWeight(37, Mathf.Max(Remap(list[76]), Remap(list[77]))); //mouth_suck_ul mouth_suck_ur smr.SetBlendShapeWeight(38, Mathf.Max(Remap(list[74]), Remap(list[75]))); //mouth_suck_dl mouth_suck_dr smr.SetBlendShapeWeight(39, Remap(list[35])); //mouth_chew_c smr.SetBlendShapeWeight(40, Remap(list[34])); //jaw_thrust_c smr.SetBlendShapeWeight(41, Remap(list[73])); //mouth_stretch_c smr.SetBlendShapeWeight(42, Remap(list[32])); //jaw_sideways_l smr.SetBlendShapeWeight(43, Remap(list[33])); //jaw_sideways_r smr.SetBlendShapeWeight(44, Remap(list[38])); //brow_raise_c smr.SetBlendShapeWeight(45, Remap(list[22])); //eye_blink2_r smr.SetBlendShapeWeight(46, Remap(list[21])); //eye_blink2_l smr.SetBlendShapeWeight(47, Remap(list[0])); //brow_lower_l smr.SetBlendShapeWeight(48, Remap(list[27])); //brow_lower_r smr.SetBlendShapeWeight(49, Mathf.Max(Remap(list[31]), Remap(list[29]))); //eye_downLidRaise_r eye_upLidRaise_r smr.SetBlendShapeWeight(50, Mathf.Max(Remap(list[30]), Remap(list[28]))); //eye_downLidRaise_l eye_upLidRaise_l yield return new WaitForSeconds(.07f); private float Remap(float v) GUI.enabled = coroutine == null; if (GUILayout.Button('Begin', GUILayout.Width(200f), GUILayout.Height(50f))) coroutine = StartCoroutine(ExecuteCoroutine()); GUI.enabled = coroutine != null; if (GUILayout.Button('Stop', GUILayout.Width(200f), GUILayout.Height(50f))) StopCoroutine(coroutine);
|
