谷歌语音识别弱日期转录 [英] google speech recognition weak date transcription

问题描述

我正在使用具有谷歌语音模型(de-DE)的当前google asr/tts，在 date 提取的某些使用情况下遇到错误的结果.

I am using currently google asr/tts with german speech model (de-DE) and experience wrong results in certain usage scenarios of date extractions.

我真的很想知道其他人是否会有类似的结果.

I am really keen on to know whether others might have similar results.

让我给你举一些例子:

我是说:

"der 1.10.1905"->< 1.10195 11095"

"der 1.10.1905" -> "1. 10195 11095"

"9.5.78"；->90587

"9.5.78" -> 90587

"22.11.98"；->22.11 89

"22.11.98" -> 22.11 89

但是:

" 22.98年11月"->"98年11月22日"

"22. November 98" -> "22 November 98"

当我完全限定月份字词时，一切正常.

When I fully qualify the month word it works all fine.

我还检查了使用提示进行优化的建议方法，没有任何改进

I also checked the proposed way to optimize by using hints, without any improvement

"speechContexts": [
            {
              "phrases": [
                "$FULLDATE"
              ]
            }
          ]

这是必须接受的东西吗?或者我有什么可以尝试的吗?

Is this something one has to accept or is there anything that I can try on top?

欢呼安德烈

推荐答案

我的结果与使用示例时的结果相同.但是，如果讲话者改为说 ein tausend neun hundert acht und neunzig ，它确实可以正确转录.

I have the same results as you have when using your example. But it does transcribe correctly if the speaker says ein tausend neun hundert acht und neunzig instead.

出于某种原因，似乎在德语中，API无法识别说话者使用几百个来表达数千个(IE 198.88 ，而不是 1900九十八).

It seems that, for some reason, in German, the API doesn't recognize when the speaker uses hundreds to express thousands (I.E. nineteen hundred ninety eight instead of one thousand nine hundred ninety eight).

我不懂德语，也无法确认这种说数字/日期的方式是否是官方的，但是如果您确定德语是官方接受的话，那么我建议您在问题跟踪器，并附有一些参考资料以确认这一点.

I don't know German and can't confirm if this way of speaking numbers/dates is official but if you are sure that in German, it is officially accepted, then I suggest that you create an issue on issue-tracker with some references to confirm it.

这篇关于谷歌语音识别弱日期转录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！