Litcius/Paper detail

Fast-Slow Transformer for Visually Grounding Speech

Puyuan Peng, David Harwath

2022ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)23 citationsDOI

Abstract

We present Fast-Slow Transformer for Visually Grounding Speech, or FaST-VGS. FaST-VGS is a Transformer-based model for learning the associations between raw speech waveforms and visual images. The model unifies dual-encoder and cross-attention architectures into a single model, reaping the superior retrieval speed of the former along with the accuracy of the latter. FaST-VGS achieves state-of-the-art speech-image retrieval accuracy on benchmark datasets, and its learned representations exhibit strong performance on the ZeroSpeech 2021 phonetic and semantic tasks.

Topics & Concepts

TransformerComputer scienceEncoderSpeech recognitionWaveformArtificial intelligenceGround truthBenchmark (surveying)VoltageEngineeringElectrical engineeringGeographyGeodesyTelecommunicationsOperating systemRadarMultimodal Machine Learning ApplicationsSpeech and Audio ProcessingSpeech Recognition and Synthesis
Fast-Slow Transformer for Visually Grounding Speech | Litcius