在audibook中为字幕创建时间戳 [英] Create timestamps for subtitles in audibook

问题描述

我想在句子中添加时间戳，以适合相关的有声读物. 最好使用各种语言.

I want to add timestamps to book sentences, fitting the relevant audiobook. In various languages ideally.

以下是一个示例:
傲慢与偏见
来自gutenberg项目的文本
来自Librivox的音频

Here's an example:
Pride and prejudice
text from gutenberg project
audio from Librivox

我的想法是找到一种语音识别工具，将时间戳记加在句子上(步骤1)，然后使用levenshtein距离将杂乱的转录映射到原始文本(步骤2).

My idea was to find a voice recognition tool that puts timestamps on sentences (step 1), and then map the messy transcription to the original text using levenshtein distances (step 2).

网站 https://speechlogger.appspot.com/提供了第一步的解决方案，但是它在字符输出方面受到限制.从理论上讲，我可以每分钟左右开始一次新的录制，从而使用网络自动化来完成工作，但这确实很脏.

The website https://speechlogger.appspot.com/ offers a solution to the 1st step, but it's limited in character output. I could theoritically use web automation to get the job done, by starting a new recording every minute or so, but it's really dirty.

我编写了R中的第2步脚本，并在从语音记录器获得的样本上对其进行了测试，并且可以正常运行，但是如果程序知道文本，则可以大大改善这一点，例如在阅读以训练语音识别软件时.我不会在这里先转录所有信息.

I scripted step 2 in R and tested it on a sample I got from speechlogger and it works okayish, but this could be greatly improved if the program knew the text, like when you read to train a speech recognition software. I'm not using all my information here by transcribing first.

所以我的问题是，我必须用什么其他方法来标记音频文件的时间戳，有没有办法让识别引擎知道它应该识别的内容来使我的过程更智能?

So my questions are, what alternative ways could i have to timestamp audio files, and is there a way i can make my process smarter by letting the recognition engine know what it's supposed to recognize ?

推荐答案

为此开发了许多不错的软件包，其准确性各不相同:

There are many nice software packages developed for that with various level of accuracy:

温柔-基于Kaldi的对齐器，可作为服务使用.

Gentle - Kaldi-based aligner, works as a service.

较旧的实现:

Sphinx4中的对齐器演示-Java中的CMUSphinx工具包

Aligner Demo in Sphinx4 - CMUSphinx toolkit in java

SAIL align -基于HTK的aligner，相当多的perl脚本包.

SAIL align - HTK-based aligner, quite some pack of perl scripts.

这篇关于在audibook中为字幕创建时间戳的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！