Show HN: Jarvis, a Light Table like companion for Python • Hacker News Board

Re: Show HN: Jarvis, a Light Table like companion for Python

#51

Post by koide » Fri, Jun 29, 2012, 3:07 PM UTC

obtu wrote: post #24

koide wrote: post #22

Earlier quoted context omitted.

Speech may be much looser, but a classifier to (try to) detect absolute gibberish from real content doesn't look too far fetched to me. Its only action would be to disable the subtitles by default if gibberish was detected. It may be computationally impractical though.

The problem with that is that the language model's power is already used to fix things up locally (because this is transcribed from audio). As a result it can't be used again to decide if the transcription fits the model; it's the case by design. There must be some kind of confidence metric at the end of the process, but I don't think it's possible to tell how much of the ambiguity comes from inadequacies in the phon…

I'm thinking of the following: audio track of the video ---[process (language recognition)]---> transcription ---[process (classifier based on textual language model)]---> answer to "gibberish?"

So good transcriptions would be good, regardless of the noise environment. It might give some false positives, but I expect that a good price to pay to avoid the kind of mess they create now.

Re: Show HN: Jarvis, a Light Table like companion for Python

#52

Post by gcr » Fri, Jun 29, 2012, 3:53 PM UTC

koide wrote: post #51

obtu wrote: post #24

Earlier quoted context omitted.

The problem with that is that the language model's power is already used to fix things up locally (because this is transcribed from audio). As a result it can't be used again to decide if the transcription fits the model; it's the case by design. There must be some kind of confidence metric at the end of the process, but I don't think it's possible to tell how much of the ambiguity comes from inadequacies in the phon…

I'm thinking of the following: audio track of the video ---[process (language recognition)]---> transcription ---[process (classifier based on textual language model)]---> answer to "gibberish?" So good transcriptions would be good, regardless of the noise environment. It might give some false positives, but I expect that a good price to pay to avoid the kind of mess they create now.

What does your "transcription" step mean? Either it would transscribe each word "in divy two Ellie, buy it's Elf", which produces garbage without context, or it would additionally have to use the language model to patch things up.

For example, the difference between "its" and "it's", "red" and "read", "know" and "no" is irreconciliable without understanding the rest of the sentence these trouble words appear in.

Re: Show HN: Jarvis, a Light Table like companion for Python

#53

Post by koide » Sat, Jun 30, 2012, 7:42 AM UTC

gcr wrote: post #52

koide wrote: post #51

Earlier quoted context omitted.

I'm thinking of the following: audio track of the video ---[process (language recognition)]---> transcription ---[process (classifier based on textual language model)]---> answer to "gibberish?" So good transcriptions would be good, regardless of the noise environment. It might give some false positives, but I expect that a good price to pay to avoid the kind of mess they create now.

What does your "transcription" step mean? Either it would transscribe each word "in divy two Ellie, buy it's Elf", which produces garbage without context, or it would additionally have to use the language model to patch things up. For example, the difference between "its" and "it's", "red" and "read", "know" and "no" is irreconciliable without understanding the rest of the sentence these trouble words appear in.

Transcription is the textual output of the speech recognition process, be it phonetic, LVCSR or direct. All current applications of them do take some context in consideration, usually via a transition matrix and lots of training data.

What I'm proposing is to pass the output of speech recognition through a binary classifier that answers the question "is this text gibberish?", which is trained with the help of a textual language model, unrelated to the speech recognition pass.