Text-Free Image-to-Speech Synthesis Using Learned Segmental Units

by   Wei-Ning Hsu, et al.

In this paper we present the first model for directly synthesizing fluent, natural-sounding spoken audio captions for images that does not require natural language text as an intermediate representation or source of supervision. Instead, we connect the image captioning module and the speech synthesis module with a set of discrete, sub-word speech units that are discovered with a self-supervised visual grounding task. We conduct experiments on the Flickr8k spoken caption dataset in addition to a novel corpus of spoken audio captions collected for the popular MSCOCO dataset, demonstrating that our generated captions also capture diverse visual semantics of the images they describe. We investigate several different intermediate speech representations, and empirically find that the representation must satisfy several important properties to serve as drop-in replacements for text.


page 2

page 20

page 22

page 24

page 25


SPEECH-COCO: 600k Visually Grounded Spoken Captions Aligned to MSCOCO Data Set

This paper presents an augmentation of MSCOCO dataset where speech is ad...

Learning Word-Like Units from Joint Audio-Visual Analysis

Given a collection of images and spoken audio captions, we present a met...

Deep Multimodal Semantic Embeddings for Speech and Images

In this paper, we present a model which takes as input a corpus of image...

Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input

In this paper, we explore neural network models that learn to associate ...

Large-scale representation learning from visually grounded untranscribed speech

Systems that can associate images with their spoken audio captions are a...

Show and Speak: Directly Synthesize Spoken Description of Images

This paper proposes a new model, referred to as the show and speak (SAS)...

Hidden bawls, whispers, and yelps: can text be made to sound more than just its words?

Whether a word was bawled, whispered, or yelped, captions will typically...