Face Landmark-based Speaker-Independent Audio-Visual Speech Enhancement in Multi-Talker Environments

Abstract

In this paper, we address the problem of enhancing the speech of a speaker of interest in a cocktail party scenario when visual information of the speaker of interest is available. Contrary to most previous studies, we do not learn visual features on the typically small audio-visual datasets, but use an already available face landmark detector (trained on a separate image dataset). The landmarks are used by LSTM-based models to generate time-frequency masks which are applied to the acoustic mixed-speech spectrogram. Results show that: (i) landmark motion features are very effective features for this task, (ii) similarly to previous work, reconstruction of the target speaker's spectrogram mediated by masking is significantly more accurate than direct spectrogram reconstruction, and (iii) the best masks depend on both motion landmark features and the input mixed-speech spectrogram. To the best of our knowledge, our proposed models are the first models trained and evaluated on the limited size GRID and TCD-TIMIT datasets, that achieve speaker-independent speech enhancement in a multi-talker setting.

arXiv commentProceedings of 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

References in corpus (3)

• Adam: A Method for Stochastic Optimization
• Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation
• Deep attractor network for single-microphone speaker separation

Cited by in corpus (11)

• Neural Target Speech Extraction: An Overview
• Audio-Visual Speech Separation and Dereverberation with a Two-Stage Multimodal Network
• Deep-Learning-Based Audio-Visual Speech Enhancement in Presence of Lombard Effect
• Look Once to Hear: Target Speech Hearing with Noisy Examples
• Deep Audio-Visual Learning: A Survey
• Effective Low-Cost Time-Domain Audio Separation Using Globally Attentive Locally Recurrent Networks
• Visually-Guided Sound Source Separation with Audio-Visual Predictive Coding
• Audio-visual Speech Separation with Adversarially Disentangled Visual Representation
• Neural Spatio-Temporal Beamformer for Target Speech Separation
• An Empirical Study of Visual Features for DNN based Audio-Visual Speech Enhancement in Multi-talker Environments
• Binaural Audio Generation via Multi-task Learning