Voice processing method, apparatus, device and storage medium
View Patent ↗The present application provides a voice processing method, an apparatus, a device, and a storage medium, including: acquiring a first acoustic feature of each of N voice frames, where N is a positive integer greater than 1; applying a neural network algorithm to N first acoustic features to obtain a first mask; modifying the first mask according to VAD information of the N voice frames to obtain a second mask; and processing the N first acoustic features according to the second mask to obtain a second acoustic feature, resulting in more effective noise suppression and a lower damage to the voice.
1. A voice processing method, comprising:
acquiring a first acoustic feature of each of N voice frames, wherein N is a positive integer greater than 1;
applying a neural network algorithm to N first acoustic features to obtain a first mask;
modifying the first mask according to voice activity detection (VAD) information of the N voice frames to obtain a second mask; and
processing the N first acoustic features according to the second mask to obtain a second acoustic feature;
wherein the VAD information comprises a VAD value corresponding to each of the voice frames; and
correspondingly, before the modifying the first mask according to VAD information of the N voice frames, the method further comprises:
determining M 1 voice frames having a VAD value of 1 and P 1 voice frames having a VAD value of 0 from the N voice frames, wherein the M 1 voice frames are adjacent to the P 1 voice frames, and wherein M 1 and P 1 are positive integers greater than 1; and
smoothing the VAD value corresponding to M 2 voice frames of the M 1 voice frames and the VAD value corresponding to P 2 voice frames of the P 1 voice frames, such that the VAD value corresponding to the M 2 voice frames and the VAD value corresponding to the P 2 voice frames are changed gradually from 0 to 1 or from 1 to 0, wherein the M 2 voice frames are adjacent to the P 2 voice frames, and wherein 1≤M 2 ≤M 1 , 1≤P 2 ≤P 1 .
2. The method according to claim 1 , wherein the modifying the first mask according to the VAD information of the N voice frames comprises:
calculating a product of the VAD information and the first mask to obtain the second mask.
3. The method according to claim 1 , wherein the determining the M 1 voice frames having the VAD value of 1 and the P 1 voice frames having the VAD value of 0 from the N voice frames comprise:
determining a call type corresponding to each of the N voice frames, wherein the type comprises silence and phone;
determining a voice frame having the silence type as a voice frame having the VAD value of 0; and
determining a voice frame having the phone type as a voice frame having the VAD value of 1.
4. The method according to claim 3 , wherein M 2 and P 2 are determined by a hamming window, a triangular window or a hanning window.
5. A voice processing device, comprising:
a memory and a processor;
wherein the memory is configured to store instructions executed by the processor, such that the processor performs:
acquiring a first acoustic feature of each of N voice frames, wherein N is a positive integer greater than 1;
applying a neural network algorithm to N first acoustic features to obtain a first mask;
modifying the first mask according to voice activity detection (VAD) information of the N voice frames to obtain a second mask; and
processing the N first acoustic features according to the second mask to obtain a second acoustic feature;
wherein the VAD information comprises a VAD value corresponding to each of the voice frames; and
correspondingly, the processor is further configured to:
determine M 1 voice frames having a VAD value of 1 and P 1 voice frames having a VAD value of 0 from the N voice frames, wherein the M 1 voice frames are adjacent to the P 1 voice frames, and wherein M 1 and P 1 are positive integers greater than 1; and
smooth the VAD value corresponding to M 2 voice frames of the M 1 voice frames and the VAD value corresponding to P 2 voice frames of the P 1 voice frames, such that the VAD value corresponding to the M 2 voice frames and the VAD value corresponding to the P 2 voice frames are changed gradually from 0 to 1 or from 1 to 0, wherein the M 2 voice frames are adjacent to the P 2 voice frames, and wherein 1≤M 2 ≤M 1 , 1≤P 2 ≤P 1 .
6. The device according to claim 5 , wherein the processor is configured to:
calculate a product of the VAD information and the first mask to obtain the second mask.
7. The device according to claim 5 , wherein the processor is configured to:
determine a call type corresponding to each of the N voice frames, wherein the type comprises silence and phone;
determine a voice frame having the silence type as a voice frame having the VAD value of 0; and
determine a voice frame having the phone type as a voice frame having the VAD value of 1.
8. The device according to claim 7 , wherein M 2 and P 2 are determined by a hamming window, a triangular window or a hanning window.
9. A non-transitory storage medium, comprising: computer executable instructions for implementing following steps:
acquiring a first acoustic feature of each of N voice frames, wherein N is a positive integer greater than 1;
applying a neural network algorithm to N first acoustic features to obtain a first mask;
modifying the first mask according to voice activity detection (VAD) information of the N voice frames to obtain a second mask; and
processing the N first acoustic features according to the second mask to obtain a second acoustic feature;
wherein the VAD information comprises a VAD value corresponding to each of the voice frames; and
correspondingly, the computer executable instructions are further configured to implement:
determining M 1 voice frames having a VAD value of 1 and P 1 voice frames having a VAD value of 0 from the N voice frames, wherein the M 1 voice frames are adjacent to the P 1 voice frames, and wherein M 1 and P 1 are positive integers greater than 1; and
smoothing the VAD value corresponding to M 2 voice frames of the M 1 voice frames and the VAD value corresponding to P 2 voice frames of the P 1 voice frames, such that the VAD value corresponding to the M 2 voice frames and the VAD value corresponding to the P 2 voice frames are changed gradually from 0 to 1 or from 1 to 0, wherein the M 2 voice frames are adjacent to the P 2 voice frames, and wherein 1≤M 2 ≤M 1 , 1≤P 2 ≤P 1 .
10. The non-transitory storage medium according to claim 9 , wherein the computer executable instructions are configured to implement:
calculating a product of the VAD information and the first mask to obtain the second mask.
11. The non-transitory storage medium according to claim 9 , wherein the computer executable instructions are configured to implement:
determining a call type corresponding to each of the N voice frames, wherein the type comprises silence and phone;
determining a voice frame having the silence type as a voice frame having the VAD value of 0; and
determining a voice frame having the phone type as a voice frame having the VAD value of 1.
12. The non-transitory storage medium according to claim 11 , wherein M 2 and P 2 are determined by a hamming window, a triangular window or a hanning window.