288 results about "Lyrics" patented technology

Serving advertisements with (e.g., in) audio documents may be improved by (a) accepting at least a portion of a document including audio content, (b) analyzing the audio content to determine relevancy information for the document, and (c) determining at least one advertisement relevant to the document using at least the relevancy information and serving constraints associated with advertisements. The advertisements may be scored if more than one advertisement was determined to be relevant to the document. Then, at least one of the advertisements to be served with an ad spot for the document may be determined using at least the scores. Examples of documents include radio programs, live or recorded musical works with lyrics, live or recorded dramatic works with dialog or a monolog, live or recorded talk shows, voice mail, segments of an audio conversation, etc. The audio content may be analyzed to determine relevancy information for the document by converting the audio content to textual information using speech recognition. Then, relevancy information may be determined from the textual information.

A singing voice synthesizing method for synthesizing the singing voice from performance data is disclosed. The input performance data are analyzed as the musical information of the pitch and the length of sounds and the lyric (S2 and S3). A track as the subject of the lyric is selected from the analyzed musical information (S5). A note the singing voice is allocated to is selected from the track (S6). The length of the note is changed to suit to a song being sung (S7). The voice quality suited to the singing is selected based on e.g. the track name/sequence name (S8) and singing voice data is prepared (S9). The singing voice is generated based on the singing voice data (S10).

The invention provides a method and a device for transforming voice into melody. The method includes acquiring input voice data and music information, adjusting duration of each syllable in the voice data to enable the duration of each syllable to be aligned with duration of corresponding lyric in the music information, adjusting voice base frequency of the voice data according to tone of each note in the music information to enable each voice base frequency point to be aligned with the tone of corresponding note in the music information and combining the voice base frequency points subjected to tone adjustment and notes subjected duration adjustment to form melody data.

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.

The present invention provides a karaoke receiving device which is capable of simultaneously supporting the voice and data signals entering in a wireless manner with two sets of wireless microphones. The singer's voice data are being processed and mixed together with the background music and then transferred to an amplifier or a television or other similar audio devices. It is also possible to control the song selecting, playback, recording and similar karaoke feature by the wireless microphone keypad control. The images and lyrics signals are transferred to a display monitor from the video encoder after the data encoding. In addition, the present invention eliminates the connecting cable between the karaoke microphone and the television and also reduces the size of the microphone. Therefore, the present invention is more convenient and provides a more enjoyable experience for the users.

The invention discloses a Chinese song emotion classification method based on multi-modal fusion. The Chinese song emotion classification method comprises the steps: firstly obtaining a spectrogram from an audio signal, extracting audio low-level features, and then carrying out the audio feature learning based on an LLD-CRNN model, thereby obtaining the audio features of a Chinese song; for lyricsand comment information, firstly constructing a music emotion dictionary, then constructing emotion vectors based on emotion intensity and part-of-speech on the basis of the dictionary, so that textfeatures of Chinese songs are obtained; and finally, performing multi-modal fusion by using a decision fusion method and a feature fusion method to obtain emotion categories of the Chinese songs. TheChinese song emotion classification method is based on an LLD-CRNN music emotion classification model, and the model uses a spectrogram and audio low-level features as an input sequence. The LLD is concentrated in a time domain or a frequency domain, and for the audio signal with associated change of time and frequency characteristics, the spectrogram is a two-dimensional representation of the audio signal in frequency, and loss of information amount is less, so that information complementation of the LLD and the spectrogram can be realized.

The invention discloses a music short video generation method and device, electronic equipment and a storage medium, and relates to the field of artificial intelligence and the field of video processing. According to the specific implementation scheme, the method comprises the steps of obtaining to-be-processed song audios; obtaining a lyric text corresponding to the song audio; performing semantic analysis on lyrics in the lyric text to generate content keywords of the lyrics; obtaining video clips associated with the lyrics according to the content keywords of the lyrics; and synthesizing the song audio and the video clips associated with the lyrics to generate a corresponding music short video. According to the invention, the video material and the song audio content are analyzed, and the label information is established for association, so that the video material associated with the song is automatically found according to the label, the song audio and the associated video materialare automatically synthesized, the making difficulty of the music short video can be reduced, and the automation and intelligence of making the MV music short video are realized.

A singing voice synthesizing method synthesizes the singing voice by exploiting performance data, such as MIDI data. The input performance data are analyzed as the musical information including the pitch and the length of the sounds and the lyric (S2 and S3). If the musical information analyzed lacks in the lyric information, an arbitrary lyric is donated to an arbitrary string of notes (S9, S11, S12 and S15). The singing voice is generated based on the so donated lyric (S17).

The present disclosure the proposes a method of displaying and seeking lyrics and an portable handheld electronic device using the same. The method includes the steps of selecting an audio recording and displaying a progress indicator of the audio recording. After receiving a touch signal on the progress indicator, the device would locate the segment of lyrics of the audio recording which is based on the location of the signal on the progress indicator. Next a pop up window on the touch screen would emerge from the progress indicator and be displayed, and the lyrics would be displayed within the frame of the pop up window. The lyrics could be one line or two lines only. The audio recording and/or the lyrics could be played from the beginning of the line corresponding to the location of the touch signal on the progress indicator.

The invention relates to artificial intelligence, and discloses a song synthesis method which comprises the steps: obtaining lyric recitation audio and music score information; performing duration labeling on the lyric recitation audio through a preset voice recognition model and a lyric pinyin text to obtain recitation duration; analyzing initial acoustic parameters from the lyric recitation audio through a preset vocoder; extracting singing duration from the lyric pinyin text according to a preset initial consonant variable speed dictionary, the rhythm information and the beat information; performing speed change processing on the initial acoustic parameters according to a preset speed change algorithm, the recitation duration and the singing duration; performing formant enhancement processing on the frequency spectrum envelope after speed change to obtain an enhanced frequency spectrum envelope; performing correction processing based on the pitch information, the singing duration and the fundamental frequency after speed change to obtain a corrected fundamental frequency; and performing song synthesis processing on the processed acoustic parameters through the preset vocoder. The invention also relates to a blockchain, and the synthesized song is stored in the blockchain.

Variation over time in fundamental frequency in singing voices is separated into a melody-dependent component and a phoneme-dependent component, modeled for each of the components and stored into a singing synthesizing database. In execution of singing synthesis, a pitch curve indicative of variation over time in fundamental frequency of the melody is synthesized in accordance with an arrangement of notes represented by a singing synthesizing score and the melody-dependent component, and the pitch curve is corrected, for each of pitch curve sections corresponding to phonemes constituting lyrics, using a phoneme-dependent component model corresponding to the phoneme. Such arrangements can accurately model a singing expression, unique to a singing person and appearing in a melody singing style of the person, while taking into account phoneme-dependent pitch variation, and thereby permits synthesis of singing voices that sound more natural.

The embodiment of the invention discloses a song climax fragment identification method and device. The method comprises the following steps: sampling an audio file of a song, according to the note time value and the rhythm type of the song, dividing the sampling data of the song into sampling data of a plurality of audio paragraphs, obtaining a chord corresponding to the audio paragraph accordingto the sampling data of the audio paragraphs, determining a chord period included in the climax fragment according to the chord trend of the song and the chord corresponding to the audio paragraph, correcting the chord period included in the climax fragment according to the lyric data of the song to obtain a chord period included in the climax fragment, and finally identifying a part, corresponding to the chord period included in the climax fragment after correction, of the song as the climax fragment of the song. According to the method and the device, the climax fragments of the song are identified based on essential factors of the song, such as note time values, rhythm types and chord trends, so that the identification accuracy of the climax fragments of the song is improved.

The invention discloses an interactive lyric generation method and system based on a neural network, and the system is based on the method, and the method comprises the steps: carrying out the pre-training of a lyric generation model, inputting preprocessed lyric training data into a basic training model for training, and obtaining a lyric generation model; acquiring a lyric label set by a user and a provided first sentence of lyrics; encoding lyric data; completing the first sentence of lyrics, and inputting data codes of the lyrics provided by the user into a lyrics generation model to automatically complete lyrics sentences; inputting the completed lyric sentence into a lyric generation model to generate a candidate sentence of a next lyric sentence; selecting a candidate statement as asecond sentence of lyrics and merging the second sentence of lyrics into the first sentence of lyrics to serve as prediction input of the next sentence of lyrics; inputting the merged lyric sentencesinto a lyric generation model to generate candidate sentences of the next lyric sentence; and repeating the above steps until one segment or the whole lyric is completed. In the lyric generation process, a plurality of candidate sentences are generated for a user to select, so that the interactivity in the lyric generation process is improved.

The embodiment of the invention discloses an audio synthesis method and device, electronic equipment and a computer readable medium. The specific embodiment of the method comprises the steps of generating a second lyric based on a first lyric sent by a client; generating melody based on the second lyrics and the theme sent by the client; generating a lyric score based on the melody and the secondlyric; generating background music and dry sound based on the music score and the melody; and generating an audio based on the dry sound and the background music. According to the embodiment, efficient song synthesis is realized, and the user of the client can participate in the singing synthesis process, so that the participation interestingness of the user is increased, and the user experience is improved.

The invention discloses an audio production method and device, equipment and a storage medium, and belongs to the technical field of audio processing. The method comprises the steps that: an audio editing interface of a first audio is displayed, wherein the audio editing interface comprises at least one sentence of lyrics of the first audio and a lyrics editing control, wherein the at least one sentence of lyrics comprises a first lyric; a lyric editing operation for the first lyric on the lyric editing control is received, wherein the lyric editing operation comprises inputting a second lyric; and the first lyric in the first audio is replaced with the second lyric, so that a second audio can be generated, wherein the second audio comprises a human voice audio generated according to the second lyric. The method can simplify the manufacturing steps of the audio.

The invention provides MV production and playing methods and devices applied to karaoke. The method comprises the steps of making lyric information, an original audio of a song and an accompaniment audio of the song into a multimedia file in a streaming media way, wherein the header of the multimedia file comprises a file code applied to identifying the attribute of the song; building a corresponding relation between the multimedia file and a video file according to the attribute of the song and the style of video content to form a corresponding relation file; and storing the corresponding relation file. By using the method, the quality of an MV in the karaoke can be effectively improved, the production efficiency of the MV can be greatly improved, and the resources can be saved.

The invention provides a lyric special effect display method and device, electronic equipment and a computer readable medium, and relates to the technical field of video processing. The method comprises the steps of acquiring a to-be-displayed image sequence and music data based on lyric special effect display operation of a user, wherein the music data comprise audio data and lyrics; determininga target time point, playing a target image corresponding to the target time point in the image sequence, and determining a target lyric corresponding to the target time point in the lyrics; and adding an animation special effect to the target image, displaying the target lyrics on the target image, and playing audio data corresponding to the target lyrics. According to the embodiment of the invention, the corresponding lyrics, special effects and target images are obtained based on the target time point, the lyrics and the special effects are superimposed on the target images for display, andthe corresponding music is played at the same time, so that when a user listens to the music, the lyrics appear along with the special effects, and the user experience is better.

The invention discloses a human voice melody extraction method and system based on numbered musical notation recognition and fundamental frequency extraction, and the system applies the method, and the method comprises the steps: carrying out the binarization of a numbered musical notation file corresponding to a to-be-processed song, processing an original audio file of the song into downsampledsingle-track audio, and separating a human voice waveform from the single-track audio; identifying notes and lyric pairs in the numbered musical notation to obtain a list of lyrics and notes; retrieving a list of lyrics and notes according to the libretto file to obtain a matching result sequence of libretto and notes; selecting a note, calculating the fundamental frequency of the note according to the separated human voice waveform, calculating the frequency of each note according to the calculated fundamental frequency and the relative relation of the notes, and converting the frequency of each note into midi pitch; and translating the matching result sequence of the row lyrics and the notes to obtain a matching result sequence of the row lyrics and the notes of which the pitches are matched with the midi pitches of the notes. The human voice melody with the pitch matched with the melody can be extracted.