| Presentation # | 11 |
| Session: | ASR IV |
| Location: | Kallirhoe Hall |
| Session Time: | Friday, December 21, 13:30 - 15:30 |
| Presentation Time: | Friday, December 21, 13:30 - 15:30 |
| Presentation: |
Poster
|
| Topic: |
Speech recognition and synthesis: |
| Paper Title: |
AUDIO-VISUAL SPEECH RECOGNITION WITH A HYBRID CTC/ATTENTION ARCHITECTURE |
| Authors: |
Stavros Petridis, Imperial College London, United Kingdom; Themos Stafylakis, University of Nottingham, United Kingdom; Pingchuan Ma, Imperial College London, United Kingdom; Georgios Tzimiropoulos, University of Nottingham, United Kingdom; Maja Pantic, Imperial College London, United Kingdom |
| Abstract: |
Recent works in speech recognition rely either on connectionist temporal classification (CTC) or sequence-to-sequence models for character-level recognition. CTC assumes conditional independence of individual characters, whereas attention-based models can provide nonsequential alignments. Therefore, we could use a CTC loss in combination with an attention-based model in order to force monotonic alignments and at the same time get rid of the conditional independence assumption. In this paper, we use the recently proposed hybrid CTC/attention architecture for audio-visual recognition of speech in-the-wild. To the best of our knowledge, this is the first time that such a hybrid architecture architecture is used for audio-visual recognition of speech. We use the LRS2 database and show that the proposed audio-visual model leads to an 1.3% absolute decrease in word error rate over the audio-only model and achieves the new state-of-the-art performance on LRS2 database (7% word error rate). We also observe that the audio-visual model significantly outperforms the audio-based model (up to 32.9% absolute improvement in word error rate) for several different types of noise as the signal-to-noise ratio decreases. |