Patent
Subtitle synchronization device and subtitle synchronization method based on speech recognition
19
TL;DR: In this article, a speech recognition module is used for extracting speech in foreground voice from an audio stream, and sampling and recognizing the extracted speech to generate corresponding text information; the dynamic sampling adjustment module was used for evaluating the degree of semantic recognition of the generated text information.
read more
Abstract: Provided are a subtitle synchronization device and a subtitle synchronization method based on speech recognition. The subtitle synchronization device comprises a speech recognition module, a dynamic sampling adjustment module, a subtitle semantic comparison module, a subtitle synchronization module and a subtitle display module. The speech recognition module is used for extracting speech in foreground voice from an audio stream, and sampling and recognizing the extracted speech to generate corresponding text information; the dynamic sampling adjustment module is used for evaluating the degree of semantic recognition of the generated text information, and controlling the speech recognition module to adjust the sampling frequency according to an evaluation result to obtain text information with high degree of semantic recognition; the subtitle semantic comparison module is used for carrying out semantic matching on the text information with high degree of semantic recognition and texts of additional subtitles in multiple languages of a broadcasted video; the subtitle synchronization module is used for adjusting time information of a subtitle file according to time information of the speech if the subtitle semantic comparison module finds out a sentence corresponding to the text information of the recognized speech in the subtitle file; and the subtitle display module is used for displaying subtitles according to the time information of the adjusted subtitle file.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Patent
Simultaneous interpretation system based on speech recognition technology
Yu Yanxing
- 08 Mar 2017
TL;DR: In this paper, a simultaneous interpretation system based on a speech recognition technology is presented, which consists of a speech acquisition unit, speech recognition unit, character translation unit, text-to-speech synthesis unit, and a speech playing unit.
17
Patent
Sound signal subtitle matching method and device
Lyu Jianchi
- 31 May 2017
TL;DR: In this paper, a sound signal subtitle matching method is proposed to match sound signals with default language characters on the basis of a preset subtitle library, and the default characters are arranged and combined into default language subtitles.
8
Patent
Method and system for wearable device to identify meaning
Zheng Zhanhai
- 02 Mar 2016
TL;DR: In this paper, a method and a system for a wearable device to identify a meaning is presented, which comprises the steps of: obtaining voices emitted by a user and physiological data parameters when the user emits the voices; identifying characters of the voices, and identifying the emotion of the user according to the physiological data parameter; identifying the meaning according to characters and the user.
8
Patent
Video subtitle determining method and video subtitle determining device
Yu Xianguo,Hu Mingqing +1 more
- 26 Apr 2017
TL;DR: In this article, a video subtitle determining method and a video subtraction device are presented. And the method comprises the following steps: acquiring one or more video frame images containing original subtitles of a target video clip and audio information corresponding to the multiple video frames images, converting the audio information into corresponding text information, and converting the original subtitle of the target video frame image into a corresponding text.
7
Patent
Video caption processing method, mobile terminal and computer readable storage medium
Zhang Jiabo
- 17 Jul 2018
TL;DR: In this article, a video caption processing method is presented, which comprises the following process: when a video file is started, acquiring a preset length of audio data from the video file according to a preset rule; identifying corresponding characters from the acquired audio data; generating captions via the recognized characters; and importing the captions into the video files for playing.
7
References
Patent
Pattern recognition system
Gabriel Ilan,Jacob Goldberger +1 more
TL;DR: In this paper, a method and system for transforming a sampling rate in speech recognition systems, in accordance with the present invention, includes the steps of providing cepstral based data including utterances comprised of segments at a reference frequency, the segments being represented by CEPstral vector coefficients, converting the cepSTral vector coefficient to energy bands in logarithmic spectra, filtering the energy bands of the log-a-thm spectra to remove energy bands having a frequency above a predetermined portion of a target frequency and converting the filtered energy bands to modified
78
Patent
Method, system and computer for realizing sound-and-caption synchronization in video file
Mingxiang Cai,Wei Wang,Xingnan Wang,Wang Zhepeng,Wu Yaqiang,Chaohui Yu,Jianzhong Zhang +6 more
- 18 Aug 2010
TL;DR: In this article, a method, a system and a computer for realizing sound-and-caption synchronization in a video file is presented, which comprises the following steps of: acquiring a first sound and a first caption of the currently played video file, wherein the first sound is not matched with the first caption, the first text corresponds to a first time stamp in the video file and the first captions correspond to a second time stamp.
19
Patent
Method and system for audio and video subtitle synchronous presenting
Haiyao Yang
- 21 Mar 2012
TL;DR: In this paper, a method for presenting voices and video titles synchronously, which comprises the following steps: receiving voice information, analyzing literal content information which is obtained according to the received voice information and corresponds to the voice information; and determining whether the literal contents information that correspond to the Received Voice Information (HIs) are the same as the Received Textual Content Information (TLI).
14
Patent
Method for speech recognition system improving discrimination by using sampling velocity conversion
Zhenhua Huang,Limin Hou +1 more
- 10 Dec 2008
TL;DR: In this paper, the sampling rate is normalized before the speech is recognized, so that the sampling rates of the testing speech and the training speech are consistent to reduce the mistaken recognition rate as a result of inconsistent sampling rates.
10
Patent
Poor speech recognition method based on support vector machine
Fu Zhengjun,Yao Jinliang,Xiaohua Wang,Huang Jinhai,Zhou Jianzheng,Yuqing Zhou,Yan Junjie +6 more
- 03 Oct 2012
TL;DR: In this paper, a poor speech recognition method based on a support vector machine (SVM) classifier was proposed, which comprises the steps of firstly acquiring an input voice stream, decoding the input voice streams to be an original voice signal, and performing the preprocessing operation; conducting windowing and framing processing for the voice data after being preprocessed; extracting shifting difference cepstrum parameter characteristics from each frame speech; classifying shifting difference parameter characteristics by utilizing a Gaussian mixture model; then classifying candidate frames of the classified poor speech by utilizing SVM class
7
Related Papers (5)
Gao Jianqing,Wang Zhiguo,Hu Guoping,Hu Yu,Liu Qingfeng +4 more
- 11 Jan 2017
Ishihara Ken,Shosakai Makoto +1 more
- 25 Feb 2010
Shi Jiang,Cao Jianzhong +1 more
- 11 Jan 2017
Baoyong Fan
- 04 Jul 2012