性能测试结果

[English]

AFE

资源消耗

Algorithm Type

RAM

Average cpu loading(compute with 2 cores)

Frame Length

AEC(LOW_COST)

152.3 KB

8%

32 ms

AEC(HIGH_PERF)

166 KB

11%

32 ms

BSS(LOW_COST)

198.7 KB

6%

64 ms

BSS(HIGH_PERF)

215.5 KB

7%

64 ms

NS(NS_MODE_SSP)

27 KB

5%

10 ms

NS(nsnet1)

885 KB

25%

16 ms

NS(nsnet2)

375 KB

12%

32 ms

MISO

56 KB

8%

16 ms

AFE Layer

227 KB

WakeNet

资源消耗

Model Type

RAM

PSRAM

Average Running Time per Frame

Frame Length

Quantised WakeNet8 @ 2 channel

50 KB

1640 KB

10.0 ms

32 ms

Quantised WakeNet9 @ 2 channel

16 KB

324 KB

3.0 ms

32 ms

Quantised WakeNet9 @ 3 channel

20 KB

347 KB

4.3 ms

32 ms

性能测试

Distance

Quiet

Stationary Noise (SNR = 4 dB)

Speech Noise (SNR = 4 dB)

AEC I nterruption (-10 dB)

1 m

98%

96%

94%

96%

3 m

98%

96%

94%

94%

误触发率:12 小时 1 次

备注

我们在测试中使用了 ESP32-S3-Korvo V4.0 开发板和 WakeNet9(Alexa) 模型。

MultiNet

资源消耗

Model Type

Internal RAM

PSRAM

Average Running Time per Frame

Frame Length

MultiNet 4

16.8KB

1866 KB

18 ms

32 ms

MultiNet 4 Q8

10.5 KB

1009 KB

11 ms

32 ms

MultiNet 5 Q8

16 KB

2310 KB

12 ms

32 ms

MultiNet 6

32 KB

4100 KB

12 ms

32 ms

Model Type

Internal RAM

PSRAM

Average Running Time per Frame

Frame Length

MultiNet 7

18 KB

2920 KB

8 ms

32 ms

Word Error Rate 性能测试

Model Type

aishell test

MultiNet 5_cn

9.5%

MultiNet 6_cn

5.2%

备注

中文使用没有声调的拼音单元去计算WER。

Speech Commands 性能测试(空调控制场景)

Model Type

Distance

Quiet

Stationary Noise (SNR=5~10dB dB)

Speech Noise (SNR=5~10dB dB)

MultiNet 5_cn

3 m

88.9%

66.1%

67.5%

MultiNet 6_cn

3 m

98.8%

88.3%

88.0%

MultiNet 6_cn_ac

3 m

97.1%

95.1%

96.8%

备注

MultiNet6_cn_ac在空调场景数据集上进行了进一步的微调,所以在空调控制场景具有更好的性能。

TTS

资源消耗

Flash image size: 2.2 MB

RAM runtime: 20 KB

性能测试

CPU 负载测试(ESP32 @240 MHz):

Speech Rate

0

1

2

3

4

5

Times faster than real time

4.5

3.2

2.9

2.5

2.2

1.8

NSNET

性能测试

数据集:array_onemic_nnoise_20230608(按照亚马逊声学认证标准录制测试集)

dnsmos

nsnet1

2.4

nsnet2

2.71