Training with Imperfect Transcripts and Language Model Adaptation for ASR of TED talks
L2F/IST and LTI/CMU –
In the first part of this talk, we describe a method that was developed to take advantage of audio with imperfect transcriptions for training acoustic models. Labels that are only approximate, e.g. closed captions, are more common than carefully transcribed speech, and therefore it is useful to be able to take advantage of these types of transcriptions for training. An iterative algorithm is presented that attempts to improve the transcriptions by inserting or removing filler words and pauses, before they are handed to the training process.
In the second part of the talk, we describe an information-retrieval based language model adaptation technique, which is employed to try to improve recognition performance in topic-oriented TED lectures, together with a new technique for implicit language model interpolation.
Date: 2011-Sep-30 Time: 15:00:00 Room: 020
For more information:
INESC-ID ESR Talks – February 2023
If you are a masters/PhD student or a postdoctoral fellow, come and present your work in an informal and friendly environment – and savour some tasty snacks!
Individual talks will be 10-15 minutes plus time for feedback. Enroll on your selected date by emailing pedro.ferreira[at]inesc-id.pt.
Happening on the second Wednesday of every month (4pm-5pm):
- 15 February (Alves Redol, Room 9)
- 15 March (Alves Redol, Room 9)
- 12 April (Alves Redol, Room 9)
- 10 May (Alves Redol, Room 9)
- 14 June (Alves Redol, Room 9)
- 12 July (Alves Redol, Room 9)
We hope to see you there!