Presentation is loading. Please wait.

Presentation is loading. Please wait.

Detecting missrecognitions Predicting with prosody.

Similar presentations


Presentation on theme: "Detecting missrecognitions Predicting with prosody."— Presentation transcript:

1 Detecting missrecognitions Predicting with prosody

2 Missrecognitions - papers “Predicting automatic speech recognition performance using prosodic cues” - TooT “Generalizing prosodic prediction of speech recognition errors” – W99

3 Missrecognitions - generalities What are they? WER – Word error rate CA – concept accuracy Why it is important to detect them? User dificulty to correct system missundertandings User frustration by unnecessary confirmations or rejections

4 Prosody to the rescue!!! Prosodic features used: Fundamental frequency (f0) Energy (rms) Duration of speaker turn (dur) Pause preceding turn (ppau) Speaking rate (tempo) Silence in speaker turn (zeros)

5 Predicting Missrecognitions - results Rule based learner (RIPPER) Characteristics of missrecognitions: Higher in pitch Louder, longer Less internal space Improved prediction with prosody TooT – 6.53% vs 22.23% W99 – 22.77% vs 26.14%

6 Predicting Missrecognitions - comments Is WER a adequate measure? Do we model the ASR capabilities or its training set? Comparing with ASR confidence score learning is ok?

7 Detecting user corrections Predicting with prosody

8 User corrections - papers “Corrections in spoken dialog systems” “Identifying user corrections automatically in spoken dialog systems”

9 User corrections - generalities What are they? Why it is important to detect them? Recognized much more poorly Tuning dialog strategies ASR for hyperarticulated speech Change of initiative and confirmation strategy

10 User corrections - insights Types: REP – repetition PAR – paraphrase ADD – content added OMIT – content omitted ADD/OMIT Characterized by prosodic features associated with hyperarticulation – but not the same

11 Predicting user corrections Rule based learner on TooT corpus Features: PROS, ASR, SYS, POS, DIA 15.72% error rate on Raw+ASR+ SYS+POS+PreTurn


Download ppt "Detecting missrecognitions Predicting with prosody."

Similar presentations


Ads by Google