CN112053697B - Method and equipment for improving voice infection of customer service staff - Google Patents
Method and equipment for improving voice infection of customer service staff Download PDFInfo
- Publication number
- CN112053697B CN112053697B CN202010724834.2A CN202010724834A CN112053697B CN 112053697 B CN112053697 B CN 112053697B CN 202010724834 A CN202010724834 A CN 202010724834A CN 112053697 B CN112053697 B CN 112053697B
- Authority
- CN
- China
- Prior art keywords
- sound
- voice
- standard
- module
- customer service
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 208000015181 infectious disease Diseases 0.000 title claims description 5
- 238000012545 processing Methods 0.000 claims abstract description 18
- 238000011156 evaluation Methods 0.000 claims abstract description 7
- 238000009432 framing Methods 0.000 claims abstract description 7
- 238000007781 pre-processing Methods 0.000 claims description 7
- 230000009467 reduction Effects 0.000 claims description 2
- 230000002238 attenuated effect Effects 0.000 claims 1
- 230000006872 improvement Effects 0.000 abstract description 5
- 230000002708 enhancing effect Effects 0.000 abstract 1
- 230000008569 process Effects 0.000 description 6
- 230000008859 change Effects 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000007115 recruitment Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L19/00—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis
- G10L19/02—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis using spectral analysis, e.g. transform vocoders or subband vocoders
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L19/00—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis
- G10L19/02—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis using spectral analysis, e.g. transform vocoders or subband vocoders
- G10L19/032—Quantisation or dequantisation of spectral components
- G10L19/035—Scalar quantisation
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/003—Changing voice quality, e.g. pitch or formants
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/27—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Quality & Reliability (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a method for improving voice infectivity of customer service personnel, which realizes the improvement of the voice infectivity of the customer service personnel by the following steps: s01, scoring the voice of the customer service staff according to the feedback evaluation of the user, and selecting 10% of the voice before scoring as standard voice; s02, extracting the characteristic value of the standard sound and calculating the average value to obtain the standard characteristic value range; s03, acquiring target sound, performing pre-emphasis and framing processing, and acquiring a characteristic value same as that of standard sound; s04, judging whether the feature value of the target sound is in the standard feature value range, if so, directly using the target sound as a restored sound, and if not, performing weighting processing to enable the target sound to be close to the standard feature value range; and s05, restoring the sound data according to the weighting processing result in the step s04 to obtain sound and outputting the sound. The invention has the advantages that: the method realizes the enhancement and beautification of the infectivity of the target sound and achieves the purpose of enhancing the sound infectivity of the customer service personnel.
Description
Technical Field
The invention relates to the field of sound beautification, in particular to a method and equipment for improving sound infection of customer service personnel.
Background
The customer service personnel can not be left in the traditional industry or the current mainstream various industries operated by means of the Internet platform. Particularly, in emerging industries and high-tech industries, the technical strength and the product quality of everyone are often the same, and the quality of service is the same in this time. In the prior art, most companies are equipped with a customer service department and corresponding customer service personnel, and the department and the corresponding personnel are emphasized. The service ability of the people correspondingly has great influence on the reputation or the sales of the enterprises, and the service ability of the customer service personnel is not the skills or the infectivity. The dialect includes business knowledge, communication skills, psychology, sentiment and the like, mainly through subsequent cultivation, and the infectivity is difficult to make great changes through subsequent hard learning and training, which causes great difficulty and high cost for enterprises to recruit customer service personnel. In the prior art, equipment is adopted to beautify sound, but the beautification is usually to adjust singing tone, frequency and the like, or to change sound after the tone adjustment, and a method or equipment capable of beautifying and increasing infectivity for common voice is absent in the prior art.
Disclosure of Invention
The invention aims to solve the technical problem of how to improve the voice infectivity of customer service staff, and provides a method and equipment for improving the voice infectivity of the customer service staff aiming at the technical problem to be solved.
In order to achieve the purpose, the invention provides the following technical scheme: a method for improving the voice infectivity of customer service staff is used for realizing the improvement of the voice infectivity of the customer service staff by the following steps:
s01, scoring the voice of the customer service staff according to the feedback evaluation of the user, and selecting 10% of the voice before scoring as standard voice;
s02, extracting the characteristic value of the standard sound, calculating an average value, obtaining an error range according to the variance of the standard sound, and respectively adding and subtracting the variance value to the average value to obtain a standard characteristic value range;
s03, acquiring target sound, performing pre-emphasis and framing processing, and acquiring a characteristic value same as that of standard sound;
s04, judging whether the feature value of the target sound is in the standard feature value range, if so, directly using the target sound as a restored sound, and if not, performing weighting processing to enable the target sound to be close to the standard feature value range;
and s05, restoring the sound data according to the weighting processing result in the step s04 to obtain sound and outputting the sound.
Further, the characteristic values of the standard sound include volume, pitch, and frequency.
Further, the frequency of the target sound is an average frequency.
Further, the frequency of the target sound is reduced or enhanced.
Further, the pre-emphasis process is implemented by a pre-emphasis digital filter.
The invention also aims to provide equipment for improving the voice infectivity of customer service personnel, which comprises a voice acquisition module, a preprocessing module, a comparison judgment module, a voice beautifying module, a voice restoration module and a voice output module, wherein the voice acquisition module is used for acquiring target voice; the preprocessing module is used for acquiring a voice signal of a target sound, performing pre-emphasis and framing processing, and acquiring a characteristic value identical to that of a standard sound; the comparison judging module is used for comparing the acquired characteristic value of the target sound with the characteristic value of the standard sound and judging whether the characteristic value is in the range of the standard sound; the voice beautification module is used for weighting the characteristic value of the target voice to enable the characteristic value to be close to the range of the standard voice; the voice restoration module is used for continuously restoring the voice according to the result of the weighting processing of the voice beautification module to obtain audio information data; and the sound output module continuously outputs the beautified sound according to the audio information data obtained by the sound restoration module.
Compared with the prior art, the invention has the beneficial effects that:
the method and the device have the advantages that the voice of the customer service staff with high evaluation is collected, the characteristic range of the standard voice is established, the target voice is collected, judged, compared and adjusted, the audio data range is close to the characteristic range of the standard voice, and the audio information data of the output voice is obtained through reduction, so that the improvement and beautification of the infectivity of the target voice are realized, and the aim of improving the voice infectivity of the customer service staff is fulfilled.
Drawings
FIG. 1 is a schematic flow chart of the method of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
As shown in the method flow shown in fig. 1, the present embodiment discloses a method for improving voice infectivity of a customer service staff, which realizes the improvement of voice infectivity of the customer service staff by the following steps:
and s01, scoring the sound of the customer service staff according to the feedback evaluation of the user, selecting 10% of the sound before scoring as standard sound, and obtaining the score according to the satisfaction degree fed back by the customer in a practical scoring mode. In other specific embodiments of the present invention, an intelligent scoring mode may also be adopted, for example, the voice of the user may be recognized through an emotion algorithm of intelligent voice recognition, so as to determine the satisfaction degree of the good account and implement the voice scoring for the customer service staff. The ranked customer service personnel voices can be selected from a larger sample size, for example, more than 200, and the voices of 10% of the customer service personnel before the scoring of the customer feedback result are selected for feature extraction.
And s02, extracting the characteristic value of the standard sound, calculating an average value, obtaining an error range according to the variance of the standard sound, and adding and subtracting the variance value from the average value to obtain a standard characteristic value range. Possibly, the characteristic values of the standard sound include volume, pitch, and frequency. It is feasible that the volume can be obtained by the amplitude of the audio information, and the frequency can be obtained by scanning and identifying the audio map by the audio identification software. And pitch is obtained by scanning the peaks of the audio map. It is thus necessary to convert the audio information data of the target sound into audio map information before obtaining the feature values.
s03, acquiring target sound, performing pre-emphasis and framing processing, and acquiring a characteristic value same as that of standard sound; it is feasible that the pre-emphasis process is implemented by a pre-emphasis digital filter. For example, by pre-emphasis digital filter H (z) =1-uz -1 The pre-emphasis is realized, the high-frequency component in the signal is improved, the frequency spectrum of the signal becomes flat, and the subsequent analysis and calculation are facilitated. In the above formula, u is generally between 0.94 and 0.97. The signal is then windowed and framed to divide the signal into short time frames.
s04, judging whether the feature value of the target sound is in the standard feature value range, if so, directly using the target sound as a restored sound, and if not, performing weighting processing to enable the target sound to be close to the standard feature value range; preferably, the frequency of the target sound is an average frequency. The adjustment process can adopt the adjustment of audio data information, and in order to improve the adjustment effect, the fitting can be carried out after the data adjustment is finished, so that the distortion condition is avoided. If the difference value is larger than the threshold value, the adjustment is continued. Wherein, the frequency of the target sound is reduced or strengthened. The adjustment of the volume can be realized through the spectrum amplitude, and the specific output can be embodied in the volume of the output equipment. In other specific embodiments of the present invention, beautification may also be performed by adjusting other feature values, the feature values may be obtained by identifying standard sounds, and the identification process may be obtained by comparing audio information of sounds with higher evaluation with audio information of other sounds by using a comparison method.
And s05, restoring the sound data according to the weighting processing result in the step s04 to obtain sound and outputting the sound, wherein the sound restoring process is an audio information data reading process and converts the processed audio information data into recognizable transmission data.
In this embodiment, the device may be configured to perform the infection of the sound, where the device includes a sound acquisition module, a preprocessing module, a comparison and judgment module, a sound beautification module, a sound restoration module, and a sound output module, where the sound acquisition module is configured to acquire the target sound; the preprocessing module is used for acquiring a voice signal of a target sound, performing pre-emphasis and framing processing, and acquiring a characteristic value identical to that of a standard sound; the comparison judging module is used for comparing the acquired characteristic value of the target sound with the characteristic value of the standard sound and judging whether the characteristic value is in the range of the standard sound; the voice beautification module is used for weighting the characteristic value of the target voice to enable the characteristic value to be close to the range of the standard voice; the voice restoration module is used for continuously restoring the voice according to the result of the weighting processing of the voice beautification module to obtain audio information data; and the sound output module continuously outputs the beautified sound according to the audio information data obtained by the sound restoration module.
Specifically, the sound acquisition device adopts a headset and the like, recording audio data can also be directly adopted for recording, the preprocessing module, the comparison and judgment module, the sound beautifying module, the sound restoration module, the sound output module and the like are realized by adopting an intelligent AI chip and a related power circuit, and programs and algorithms for realizing the functions are integrated in the chip, so that the improvement on the sound infectivity is realized.
The method and the device establish the characteristic range of the standard sound by collecting the sound of the high-evaluation customer service personnel, acquire the target sound, judge, compare and adjust the target sound to enable the audio data range to be close to the characteristic range of the standard sound, and obtain the audio information data of the output sound by restoring, so that the infectivity of the target sound is improved and beautified, and the purpose of improving the sound infectivity of the customer service personnel is achieved. The affinity and the whole infectivity of customer service personnel can be effectively improved, and the satisfaction of final customers is improved; the threshold of recruitment and election of enterprise customer service personnel can be reduced, and the enterprise operation cost is finally reduced; also, the technique and apparatus can be used by a variety of persons who want to change their own voice appeal, with the result that they are effective.
The embodiments of the present invention have been described in detail above with reference to the accompanying drawings, but the present invention is not limited to the described embodiments. It will be apparent to those skilled in the art that various changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, and the scope of protection is still within the scope of the invention.
Claims (4)
1. A method for improving the voice infectivity of customer service personnel is characterized by comprising the following steps of:
s01, scoring the voice of the customer service staff according to the feedback evaluation of the user, and selecting 10% of the voice before scoring as standard voice;
s02, extracting characteristic values of the standard sound and calculating an average value, obtaining an error range according to the variance of the standard sound, and respectively adding and subtracting variance values to the average value to obtain a standard characteristic value range, wherein the characteristic values of the standard sound comprise volume, pitch and frequency;
s03, acquiring target sound, performing pre-emphasis and framing processing, and acquiring a characteristic value same as that of standard sound;
s04, judging whether the feature value of the target sound is in the standard feature value range, if so, directly using the target sound as a restored sound, and if not, performing weighting processing to enable the target sound to be close to the standard feature value range, wherein the frequency of the target sound is an average frequency;
and s05, restoring the sound data according to the weighting processing result in the step s04 to obtain sound and outputting the sound.
2. The method for improving the sound infection of the customer service personnel according to claim 1, wherein the target sound is attenuated or enhanced by the frequency reduction method.
3. The method of claim 1, wherein the pre-emphasis is performed by a pre-emphasis digital filter.
4. The equipment for improving the voice infectivity of the customer service personnel is characterized by comprising a voice acquisition module, a preprocessing module, a comparison judgment module, a voice beautifying module, a voice restoration module and a voice output module, wherein the voice acquisition module is used for acquiring target voice; the preprocessing module is used for acquiring a voice signal of a target sound, performing pre-emphasis and framing processing, and acquiring characteristic values which are the same as those of a standard sound, wherein the characteristic values of the standard sound comprise volume, pitch and frequency; the comparison judging module is used for comparing the acquired characteristic value of the target sound with the characteristic value of the standard sound and judging whether the characteristic value is in the range of the standard sound, wherein the frequency of the target sound is the average frequency; the voice beautification module is used for weighting the characteristic value of the target voice to enable the characteristic value to be close to the range of the standard voice; the sound restoring module is used for continuously restoring the sound according to the weighting processing result of the sound beautifying module to obtain audio information data; and the sound output module continuously outputs the beautified sound according to the audio information data obtained by the sound restoration module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010724834.2A CN112053697B (en) | 2020-07-24 | 2020-07-24 | Method and equipment for improving voice infection of customer service staff |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010724834.2A CN112053697B (en) | 2020-07-24 | 2020-07-24 | Method and equipment for improving voice infection of customer service staff |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112053697A CN112053697A (en) | 2020-12-08 |
| CN112053697B true CN112053697B (en) | 2023-03-31 |
Family
ID=73601576
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010724834.2A Active CN112053697B (en) | 2020-07-24 | 2020-07-24 | Method and equipment for improving voice infection of customer service staff |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112053697B (en) |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5122598B2 (en) * | 2010-03-30 | 2013-01-16 | 株式会社コナミデジタルエンタテインメント | Speech input evaluation system, control method for speech input evaluation system, and program |
| CN104202491B (en) * | 2014-09-25 | 2017-03-22 | 北京橙鑫数据科技有限公司 | Method for handling customer service telephone call and device thereof |
| CN106531187A (en) * | 2016-11-09 | 2017-03-22 | 上海航动科技有限公司 | Call center performance assessment method and system |
| CN108564968A (en) * | 2018-04-26 | 2018-09-21 | 广州势必可赢网络科技有限公司 | A kind of method and device of evaluation customer service |
| CN109036468A (en) * | 2018-11-06 | 2018-12-18 | 渤海大学 | Speech-emotion recognition method based on deepness belief network and the non-linear PSVM of core |
| CN109410971B (en) * | 2018-11-13 | 2021-08-31 | 无锡冰河计算机科技发展有限公司 | Method and device for beautifying sound |
-
2020
- 2020-07-24 CN CN202010724834.2A patent/CN112053697B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112053697A (en) | 2020-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105611477B (en) | The voice enhancement algorithm that depth and range neutral net are combined in digital deaf-aid | |
| CN107154257A (en) | Customer service quality evaluating method and system based on customer voice emotion | |
| CN107610712B (en) | Voice enhancement method combining MMSE and spectral subtraction | |
| CN110136709A (en) | Audio recognition method and video conferencing system based on speech recognition | |
| CN107705791A (en) | Caller identity confirmation method, device and Voiceprint Recognition System based on Application on Voiceprint Recognition | |
| CN107221339A (en) | Based on gain compensation audiphone voice quality W PESQ method for objectively evaluating | |
| CN110277087A (en) | A kind of broadcast singal anticipation preprocess method | |
| CN111489763B (en) | GMM model-based speaker recognition self-adaption method in complex environment | |
| CN104157294B (en) | A kind of Robust speech recognition method of market for farm products element information collection | |
| CN108877807A (en) | A kind of intelligent robot for telemarketing | |
| Dubey et al. | Comparison of subjective and objective speech quality assessment for different degradation/noise conditions | |
| CN112053697B (en) | Method and equipment for improving voice infection of customer service staff | |
| CN112614510B (en) | Audio quality assessment method and device | |
| CN111554325B (en) | Voice recognition method and system | |
| Singh et al. | Novel feature extraction algorithm using DWT and temporal statistical techniques for word dependent speaker’s recognition | |
| CN106971712A (en) | A kind of adaptive rapid voiceprint recognition methods and system | |
| CN111009262A (en) | Voice gender identification method and system | |
| CN113516987B (en) | Speaker recognition method, speaker recognition device, storage medium and equipment | |
| WO2021217979A1 (en) | Voiceprint recognition method and apparatus, and device and storage medium | |
| CN113411456B (en) | Voice quality assessment method and device based on voice recognition | |
| Tantibundhit et al. | Joint time–frequency segmentation algorithm for transient speech decomposition and speech enhancement | |
| CN106981287A (en) | A kind of method and system for improving Application on Voiceprint Recognition speed | |
| Joshi et al. | Sub-Band Level Histogram Equalization for Robust Speech Recognition. | |
| CN111048072A (en) | Voiceprint recognition method applied to power enterprises | |
| CN106971735A (en) | A kind of method and system for regularly updating the Application on Voiceprint Recognition of training sentence in caching |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |