185 results about "Vocal music" patented technology

Audiovisual performances, including vocal music, are captured and coordinated with those of other users in ways that create compelling user experiences. In some cases, the vocal performances of individual users are captured (together with performance synchronized video) on mobile devices, television-type display and / or set-top box equipment in the context of karaoke-style presentations of lyrics in correspondence with audible renderings of a backing track. Contributions of multiple vocalists are coordinated and mixed in a manner that selects for visually prominent presentation performance synchronized video of one or more of the contributors. Prominence of particular performance synchronized video may be based, at least in part, on computationally-defined audio features extracted from (or computed over) captured vocal audio. Over the course of a coordinated audiovisual performance timeline, these computationally-defined audio features are selective for performance synchronized video of one or more of the contributing vocalists.

A method of evaluating a vocal performance of a singer of a karaoke apparatus includes extracting a voice energy, extracting a reference pitch, and comparing the voice energy and an energy corresponding to the reference pitch and evaluating the vocal performance of the singer.

Despite many practical limitations imposed by mobile device platforms and application execution environments, vocal musical performances may be captured and continuously pitch-corrected for mixing and rendering with backing tracks in ways that create compelling user experiences. In some cases, the vocal performances of individual users are captured on mobile devices in the context of a karaoke-style presentation of lyrics in correspondence with audible renderings of a backing track. Such performances can be pitch-corrected in real-time at a portable computing device (such as a mobile phone, personal digital assistant, laptop computer, notebook computer, pad-type computer or netbook) in accord with pitch correction settings. In some cases, pitch correction settings include a score-coded melody and / or harmonies supplied with, or for association with, the lyrics and backing tracks. Harmonies notes or chords may be coded as explicit targets or relative to the score coded melody or even actual pitches sounded by a vocalist, if desired.

A computer implemented method of organizing a set of documents, comprising receiving verbal utterances from a user; processing the verbal utterances using gender analysis routines, thereby determining a verbally identified gender of the user; processing the verbal utterances using speech recognition routines, thereby determining the content of a search query uttered by the user; identifying a set of documents responsive to the search query based at least in part upon the content of the search query uttered by the user; assigning a score to each identified document based upon a correlation between gender-usage data for each document in the set and the verbally identified gender of the user, the gender-usage data describing at least one of a number and frequency of users who have previously accessed the document who are of a particular gender; and organizing the documents based at least in part on the assigned score.

Vocal musical performances may be captured and, in some cases or embodiments, pitch-corrected and / or processed in accord with a user selectable vocal effects schedule for mixing and rendering with backing tracks in ways that create compelling user experiences. In some cases, the vocal performances of individual users are captured on mobile devices in the context of a karaoke-style presentation of lyrics in correspondence with audible renderings of a backing track. Such performances can be pitch-corrected in real-time at the mobile device in accord with pitch correction settings. Vocal effects schedules may also be selectively applied to such performances. In these ways, even amateur user / performers with imperfect pitch are encouraged to take a shot at “stardom” and / or take part in a game play, social network or vocal achievement application architecture that facilitates musical collaboration on a global scale and / or, in some cases or embodiments, to initiate revenue generating in-application transactions.

A system provided herein may perform automatic temporal alignment between music audio signal and lyrics with higher accuracy than ever. A non-fricative section extracting 4 extracts non-fricative sound sections, where no fricative sounds exist, from the music audio signal. An alignment portion 17 includes a phone model 15 for singing voice capable of estimating phonemes corresponding to temporal-alignment features. The alignment portion 17 performs an alignment operation using as inputs temporal-alignment features obtained from a temporal-alignment feature extracting portion 11, information on vocal and non-vocal sections obtained from a vocal section estimating portion 9, and a phoneme network SN on conditions that no phonemes exist at least in non-vocal sections and that no fricative phonemes exist in non-fricative sound sections.

User interface techniques provide user vocalists with mechanisms for seeding subsequent performances by other users (e.g., joiners). A seed may be a full-length seed spanning much or all of a pre-existing audio (or audiovisual) work and mixing, to seed further contributions of one or more joiners, a user's captured media content for at least some portions of the audio (or audiovisual) work. A short seed may span less than all (and in some cases, much less than all) of the audio (or audiovisual) work. For example, a verse, chorus, refrain, hook or other limited “chunk” of an audio (or audiovisual) work may constitute a seed. A seeding user's call invites other users to join the full-length or short-form seed by singing along, singing a particular vocal part or musical section, singing harmony or other duet part, rapping, talking, clapping, recording video, adding a video clip from camera roll, etc. The resulting group performance, whether full-length or just a chunk, may be posted, livestreamed, or otherwise disseminated in a social network.

A user interface apparatus for displaying areas having vocal or instrumental unit signals that are included in an input musical tone signal. Display locations, for display on a display screen that has a localization-frequency plane, are calculated for the input musical tone signal based on localization information of each frequency band. Then, the primary level distributions, in which the levels of the frequency band corresponding to each display location are expanded and obtained using a specified distribution in each of the frequency bands, is calculated. The secondary level distribution is calculated in this manner by aggregating the frequency bands for each respective display location. Said secondary level distribution is displayed in three dimensions (the localization axis, the frequency axis, and the level axis) and viewed from the level axis direction. Therefore, the areas, in which the vocal or instrumental units exist in a grouped state, can be easily identified.

A broadcast music channel for a one-to-many broadcasting infrastructure, broadcasting at least vocal and instrumental parts of musical performances to currently connected users of the channel, and supporting a user operated interactive control allowing each user independently to remove a vocal part of a current performance if desired. The vocals can be replaced by subtitles, again under interactive control, and the result is a regular music channel that can be used for karaoke if and when desired.

The embodiment of the invention discloses an individualized song recommending system based on vocal music characteristics. The method includes the following steps of extracting characteristics, wherein the voice register characteristics, speed characteristics and tone characteristics of singing data are extracted, the voice register characteristics include absolute voice register and relative voice register, the speed characteristics include the number of beats per minute, and the tone characteristics include a Gaussian mixture model of Mel frequency cepstrum coefficient training; recommending songs systematically, wherein a corresponding song in a music library is found through a key sound matching algorithm according to a snatch sung by a user, and voice register conformity detection, song conformity detection and singer conformity detection are conducted. Singer recommending and song recommending are conducted according to extracted user characteristics. By means of the method, whether a current song is suitable for being sung by the user or not can be evaluated, and singers matched with the user vocal music ability and songs suitable for being sung by the user are further recommended. From the perspective of user singing, the traditional music recommending range is expanded, and higher practical value is achieved.

Techniques have been developed to facilitate the livestreaming of group audiovisual performances. Audiovisual performances including vocal music are captured and coordinated with performances of other users in ways that can create compelling user and listener experiences. For example, in some cases or embodiments, duets with a host performer may be supported in a sing-with-the-artist style audiovisual livestream in which aspiring vocalists request or queue particular songs for a live radio show entertainment format. The developed techniques provide a communications latency-tolerant mechanism for synchronizing vocal performances captured at geographically-separated devices (e.g., at globally-distributed, but network-connected mobile phones or tablets or at audiovisual capture devices geographically separated from a live studio).

A vocal and / or instrumental training system can include a sound storage database having a plurality of model sound recordings, such as recordings of various wild game calls, stored therein. A user can select one of the model sound recordings to emulate, and provide audio input, such as the user's vocal performance of a wild game call, in an attempt to emulate the selected model sound recording. The audio input can be received by an audio input device, and recorded by a recording device. Audio characteristics, such as pitch, tone, timbre, cadence, rhythm, beat and / or amplitude, of the recorded audio input can be compared with the corresponding audio characteristics of the selected model sound recording. Results of the comparison can be graphically displayed on a sound graph.

There is provided a post processing technique or method for separation algorithms to separate vocals from monaural music recordings. The method comprises detecting traces of pitched instruments in a magnitude spectrum of a separated voice using Hough transform and removing the detected traces of pitched instruments using median filtering to improve the quality of the separated voice and to form a new separated music signal. The method further comprises applying adaptive median filtering techniques to remove the identified Hough regions from the vocal spectrogram producing separated pitched instruments harmonics and new vocals while adding the separated pitched instruments harmonics to a music signal separated using any separation algorithm to form the new separated music signal.

The invention discloses a vocal music learning electronic auxiliary pronunciation system. The system comprises a mouth shape and tongue position image acquisition module, an audio acquisition module, a data processing module, a pronunciation standard assessment module, a mouth shape standard assessment module, a pitch extraction module, a beat extraction module, a note pitch and note duration model construction module, a singing ability primary assessment module, a comprehensive assessment module, a pronunciation auxiliary guidance module, a training scheme generation module, and a central processor. According to the system, data acquisition and assessment in a whole vocal music ability detection process are accomplished based on a computer system, the automation degree is high, the coverage is wide, the detection and analysis of the position and stability condition of throat, the timbre condition of sound, the audio penetrating force condition, the overtone application condition, and the maintenance condition of pronunciation in singing are accomplished at one time, and a targeted training scheme can be obtained.

A music based video game in which a game player's singing performance is digitally sampled while the player performs a free-form vocal over a prerecorded musical composition. Aspects of the game player's free-form vocal performance are compared with predetermined criteria. For example, the vocal performance may be compared with tempo and key information to generate performance evaluation data. The performance evaluation data may be used to present performance feedback to the game player while the game player is singing.

Provided is a music practice supporting appliance, which receives an input of sounds of a musical instrument, vocal music, and the like and acquiring and displaying deviation of those sounds inputted by a practicing person from preset reference sounds with high precision so that a change in the deviation is easier to grasp for the practicing person than in the case of a conventional music practice supporting appliance. In the music practice supporting appliance, a musical interval of an input signal of sound inputted in a signal input unit (1) is detected by a musical interval detecting unit (6), and a sound volume thereof is detected by a sample-and-hold unit (8). The detected pieces of data are displayed on a display unit (11). Since the musical intervals and the sound volumes of the sounds of the musical instrument can be objectively displayed, the display is useful in practices of playing the musical instrument. Also, by storing the data in a memory unit, practiced contents can be confirmed later.

The invention belongs to the technical field of singing skill detection, and discloses a vocal music teaching singing skill detecting system. The vocal music teaching singing skill detection system includes a sound acquisition module, a throat detecting module, a feature signal collecting module, a respiratory frequency acquisition module, a sound processing module, a database, a comparison evaluation module, and an expert evaluation module. The invention completes the acquisition and evaluation of the data in the whole vocal music skill detection process on the basis of the computer system, and has high automation degree and wide coverage; the system can perform the anti-noise pitch feature extraction, the note pitch model set and the note time value model set parameter training through the sound processing module, has high recognition rate and calculation speed, and can improve the accuracy of acquired sound audios; the invention can meet the use requirements of different vocal musictrainings, compares the acquired audio data with a standard audio so as to allow a student to intuitively understand his training defects.

The present invention relates to a device for controlling local music playing by using speech. The device comprises an audio signal acquisition unit, a speech recognition judgment unit, an information analysis unit, an execution unit and a music storage unit, wherein the audio signal acquisition unit is used for acquiring external speech information, the speech recognition judgment unit is used for carrying out speech recognition on the external speech information to obtain a music playing control instruction, the information analysis unit is used for analyzing music track number and volume information contained in the music playing control instruction, the execution unit is used for playing corresponding music according to the music track number and volume information, and the music storage unit is used for storing local music data. According to the device of the invention, smart home music playing control is carried out based on an emotion recognition and speech recognition-combined recognition mode, and home atmosphere can be improved.

The invention discloses an automatic piano adjusting device for vocal music performance and an adjusting method of the automatic piano adjusting device. The automatic piano adjusting device comprises a piano frame, piano keys and a top cover hinged to the top of the piano frame, wherein peripheral plates are arranged on two sides of the piano frame and located on two sides of the piano keys, slide rails are arranged in the peripheral plates, a level gauge is arranged on the surface of the top of the piano frame, an air cylinder is arranged on the right side of the piano frame, a support frame is mounted at the output end of the air cylinder, the other end of the support frame is mounted at the bottom of the top cover, a horizontal platform is glidingly connected to the peripheral plates, a pedal device is arranged at the bottom of the horizontal platform, piano feet are arranged at the bottoms of the piano frame and the horizontal platform, and electric telescopic poles are arranged on the piano feet, so that the included angle formed between the piano frame and the top cover can be automatically adjusted. The horizontal height of the device can be automatically adjusted under the combined action of the level gauge and the electric telescopic poles. The automatic piano adjusting device has the advantages of being reasonable in structure design, simple to operate and the like and can rapidly and effectively adjust the piano device for vocal music performance.

The invention, which discloses the technical field of music training, discloses a vocalization training apparatus for vocal music. The apparatus comprises a pedestal; a placing groove is formed in the top of the pedestal; a rotating shaft is arranged at one end of an inner cavity of the placing groove; and a microphone sleeves the outer wall of the rotating shaft. A machine body and a display screen are arranged at the left side of the placing groove; the display screen is arranged below the display screen; a switch button is arranged at the bottom of the outer wall of the machine body; and control buttons are arranged uniformly at the right side of the switch button. A touch screen is arranged on the top of the outer wall of the machine body; and a playing device is arranged at the right side of the touch screen. The identification rate is high and the calculation speed is fast; using demands of different vocal music training can be satisfied; and collected audio data are compared with a standard voice frequency, so that students can get own training defect information visually. Therefore, comprehensiveness of training guidance is improved and the learning efficiency is improved substantially.

The invention, whichrelates to the field of vocal music breathing practice tools, discloses a vocal music breath training instrument comprising a scale rod, a placing groove formed in the scale rod, afirst falling pipe arranged in the placing groove, a transverse column communicated with the bottom of the first falling pipe, second falling pipes arranged at the two ends of the transverse column,a load bearing box connected to the bottoms of the second falling pipes, an extending hole formed in the outer side of the inner bottom of the load bearing box, a bottom column arranged in the middleof the inner bottom face, a supporting column rotating on the bottom column, a containing groove formed in the top end of the supporting column, and breathing devices detachably arranged on the opposite sides, close to two vertical rods, of the load bearing box. With thefirst falling pipe in the placing groove, the transverse column and the second falling pipes, small balls and the like can be added into the load-bearing box to enhance the respiratory exercise resistance, so that corresponding exercises are made for respiratory foundations of different people. The breathing devices are arranged on the opposite sides, close to the two vertical rods, of the load bearing box and thus two persons can compare the breathing forces, so that the subjectivity and fun of breathing training are improved.

A recording of a lesson on how to play an instrumental portion of a song that has a plurality of song sections and the one or more of the song sections contains the instrumental portion. The lesson comprises instructions how to play the instrumental portion for each song section, and the instructions are arranged in a chronological sequence as the song sections occur in the song. The recording may also include a recording of a recreation of the song, and in an instruction for each song section there is a recording of the recreated song section that occurs at a beginning of the instruction. The recording may also include a recording of the recreated song section that has the instrumental portion removed and can be played back without interruption so a student may play the instrumental portions as the recording is played.

An embodiment is related to automatic summarization for digital audio raw data (12), more specifically, for identifying pure music and vocal music (40,60) from digital audio data by extracting distinctive features from music frames (73,74,75,76), designing a classifier and determining the classification parameters (20) using adaptive learning / training algorithm (36), and identifying music into pure music or vocal music according to the classifier. For pure music, temporal, spectral and cepstral features are calculated to characterise the musical content, and an adaptive clustering method is used to structure the musical content according to calculated features. The summary (22,24,26,48,52,70,72) is created according to clustered result and domain-based music knowledge (50,150). For vocal music, voice related features are extracted and used to structure the musical content, and similarly, the music summary is created in terms of structured content and heuristic rules related to music genres.

The invention provides a resonant sound making helmet which comprises a helmet body and a power supply device, sound making resonant modules, a communication module and a control circuit board which are arranged on the helmet body. The power supply device supplies power to the sound making resonant modules and the communication module. A voice module is connected with external audio equipment through the communication module. Each sound making resonant module comprises a vibration system, a magnetic circuit system and a fixing block. The vibration systems are provided with coils, one end of each fixing block is connected to the corresponding coil, and the other end of each fixing block is fixed to the helmet body. When the resonant sound making helmet works, the magnetic circuit systems drive the fixing blocks to vibrate, accordingly the helmet body conducts synchronous vibration, the sound making resonant modules and the helmet body are made to generate resonance, the sound making medium and a sound cavity are different from those of an existing helmet, the sound quality is good, the whole helmet body forms the sound cavity, vibration and sound production are conducted without the air medium, the resonant sound making helmet can spread sound at the frequency of 360 degrees, no box body standing wave exists, original sound quality of various pieces of vocal music is maintained, and the sound quality of all frequency bands is extremely clear.

The invention discloses a vocal music singing vital capacity training device, and belongs to the technical field of vocal music singing auxiliary tanning devices; the vocal music singing vital capacity training device comprises a table body, wherein a bearing plate is arranged on the table body; a groove is formed in the surface of the bearing plate; an inhaling barrel is arranged in the groove; afirst connection port and a second connection port are formed in the bottom of the inhaling barrel; a first pipe body is detachably connected to the second connection port, and a first piston is arranged in the inhaling barrel; an exhaling barrel is arranged on the surface of the bearing plate; a barrel cover is arranged at one end of the exhaling barrel; a guide rod is fixedly connected to the inner side of the barrel cover; the end of the guide rod penetrates through a spring, a heavy block and a second piston in sequence and is connected with a limiting piece; the other end of the inhalingbarrel is detachably connected with a second pipe body; the other end of the first pipe body and the other end of the second pipe body are communicated with a main pipe body, and the other end of themain pipe body is provided with a gas collecting opening. Through inhaling and exhaling training, the vital capacity of a trainer can be improved effectively, and the vocal music singing level is further improved.

A user interface apparatus for displaying areas having vocal or instrumental unit signals that are included in an input musical tone signal. Display locations, for display on a display screen that has a localization-frequency plane, are calculated for the input musical tone signal based on localization information of each frequency band. Then, the primary level distributions, in which the levels of the frequency band corresponding to each display location are expanded and obtained using a specified distribution in each of the frequency bands, is calculated. The secondary level distribution is calculated in this manner by aggregating the frequency bands for each respective display location. Said secondary level distribution is displayed in three dimensions (the localization axis, the frequency axis, and the level axis) and viewed from the level axis direction. Therefore, the areas, in which the vocal or instrumental units exist in a grouped state, can be easily identified.

The invention discloses a vocal music breath practicing device. The invention belongs to the technical field of vocal music practice tools. The problem that a vocal music practicer is difficult to master the breath practicing strength and the breath amount of blowing is solved. The device is characterized in that the device comprises a training cylinder, a bottom cover, an air blowing nozzle, an outer sleeve, an exhaust head and an adjusting turncap; the bottom of the training cylinder is connected with the bottom cover; a boss is annularly arranged on the outer wall of the training cylinder;the outer sleeve is arranged outside the training cylinder above the boss; a diversion hole is formed in the top end of the training cylinder; the top of the outer sleeve is connected with the exhausthead; the middle of the top end of the exhaust head is connected with the adjusting turncap through rivets; the outer sleeve is arranged on the training cylinder, and the adjusting turncap is rivetedon the exhaust head at the top of the outer sleeve, so that an exhaust gear be conveniently adjusted and a practicer conveniently and flexibly adjust the breath, the expiration amount of the practicer can be conveniently measured and the breath can be conveniently adjusted by controlling the exhaust amount, and the device is convenient and fast to operate.

The invention discloses a vocal music teaching singing skill detection system. The invention specifically relates to the technical field of music teaching detection. The system comprises a server fordata processing and analysis, the output end of the server is connected with a student end for singing students to operate; the input end of the student terminal is connected with a sound acquisitionmodule used for audio recording, a throat detection module used for detecting the throat position condition during singing, and a body cavity detection module used for detecting the body cavity breathing opening condition during singing. The output end of the server is connected with a sound evaluation module used for sound comparison, detection and evaluation and a skill evaluation module used for evaluating singing skills in combination with collected throat data and body cavity data. According to the invention, sound evaluation is carried out through the sound evaluation module, the skill evaluation module compares the physical sign information with standard singing physical sign information, singing skill evaluation is carried out, the evaluation result is more accurate, and subsequenttargeted practice is facilitated.

The invention discloses a multimedia data processing method and device and a readable storage medium, and the method comprises the steps: obtaining a target audio recognition model associated with original audio data when the original audio data in a multimedia file is obtained; inputting the original audio data into a target vocal music separation model, and performing vocal music separation on the original audio data by the target vocal music separation model to obtain a first type of audio track associated with the first object and a second type of audio track associated with the second object; acquiring voice data of the first object from the first type of audio track, inputting the voice data of the first object into a target voice recognition model, and performing text recognition on the voice data of the first object by the target voice recognition model to obtain a text recognition result of the first object; and determining the audio type of the original audio data based on the text recognition result, and storing the audio data associated with the second object in the second type of audio track. According to the invention, the accuracy of audio data identification can be improved.

The invention relates to a vocal music breath training instrument which effectively solves the technical problem that an existing respiratory training instrument cannot achieve a good respiratory training effect and comprises a first rectangular shell, breathing devices are installed at the two ends of the first rectangular shell, the instrument comprises a second rectangular shell, a rotating roller is rotationally installed on the second rectangular shell and connected with a small motor, a slider is slidably connected in a breathing part, the lower end of the slider is connected with a cylindrical tube, a magnetic head is fixed at the bottom of the cylindrical tube, a detection cloth layer is sleeved on the rotating roller, the detection cloth layer comprises a middle magnetic force layer, a plurality of magnetic force bins are arranged in the middle of the magnetic force layer, powder layers are placed in the magnetic force bins, a transparent upper sealing layer is arranged at theupper end of the magnetic force layer, a lower sealing layer is arranged at the lower end of the magnetic force layer, an opening is formed in one side of the second rectangular shell, a powder removing device is mounted at an opening, a detachable plate capable of being opened is arranged on one side of the second rectangular shell, a detection sensor is installed in the first rectangular shell,and an angle sensor is installed at the position of the rotating roller. The vocal music breath training instrument is easy to operate, diversified in function and low in cost and has practicability.