Detail publikace

Multimodal Phoneme Recognition of Meeting Data

Originální název

Multimodal Phoneme Recognition of Meeting Data

Anglický název

Multimodal Phoneme Recognition of Meeting Data

Jazyk

en

Originální abstrakt

This paper describes experiments in automatic recognition of context-independent phoneme strings from meeting data using audio-visual features. Visual features are known to improve accuracy and noise robustness of automatic speech recognizers. However, many problems appear when not ``visually clean'' data is provided, such as data without limited variation in the speaker's frontal pose, lighting conditions, background, etc. The goal of this work was to test whether visual information can be helpful for recognition of phonemes using neural nets. While the audio part is fixed and uses standard Mel filter-bank energies, different features describing the video were tested: average brightness, DCT coefficients extracted from region-of-interest (ROI), optical flow analysis and lip-position features. The recognition was evaluated on a sub-set of IDIAP meeting room data. We have seen small improvement when compared to purely audio-recognition, but further work needs to be done especially concerning the determination of reliability of video features.

Anglický abstrakt

This paper describes experiments in automatic recognition of context-independent phoneme strings from meeting data using audio-visual features. Visual features are known to improve accuracy and noise robustness of automatic speech recognizers. However, many problems appear when not ``visually clean'' data is provided, such as data without limited variation in the speaker's frontal pose, lighting conditions, background, etc. The goal of this work was to test whether visual information can be helpful for recognition of phonemes using neural nets. While the audio part is fixed and uses standard Mel filter-bank energies, different features describing the video were tested: average brightness, DCT coefficients extracted from region-of-interest (ROI), optical flow analysis and lip-position features. The recognition was evaluated on a sub-set of IDIAP meeting room data. We have seen small improvement when compared to purely audio-recognition, but further work needs to be done especially concerning the determination of reliability of video features.

BibTex


@inproceedings{BUT17133,
  author="Petr {Motlíček} and Jan {Černocký}",
  title="Multimodal Phoneme Recognition of Meeting Data",
  annote="This paper describes experiments in automatic recognition of
context-independent phoneme strings from meeting data using
audio-visual features. Visual features are known to improve accuracy
and noise robustness of automatic speech recognizers. However, many
problems appear when not ``visually clean'' data is provided, such as
data without limited variation in the speaker's frontal pose, lighting
conditions, background, etc. The goal of this work was to test whether
visual information can be helpful for recognition of phonemes using
neural nets. While the audio part is fixed and uses standard Mel
filter-bank energies, different features describing the video were
tested: average brightness, DCT coefficients extracted from
region-of-interest (ROI), optical flow analysis and lip-position
features. The recognition was evaluated on a sub-set of IDIAP meeting
room data. We have seen small improvement when compared to purely
audio-recognition, but further work needs to be done especially
concerning the determination of reliability of video features. 
", address="Springer Verlag", booktitle="7th International Conference, TSD 2004 Brno, Czech Republic, September 2004 Proceedings", chapter="17133", institution="Springer Verlag", journal="Lecture Notes in Computer Science", number="09", year="2004", month="june", pages="379--384", publisher="Springer Verlag", type="conference paper" }