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

This paper presents an augmentation of MSCOCO dataset where speech is added to image and text. Speech captions are generated using text-to-speech (TTS) synthesis resulting in 616,767 spoken captions (more than 600h) paired with images. Disfluencies and speed perturbation are added to the signal in order to sound more natural. Each speech signal (WAV) is paired with a JSON file containing exact timecode for each word/syllable/phoneme in the spoken caption. Such a corpus could be used for Language and Vision (LaVi) tasks including speech input or output instead of text. Investigating multimodal learning schemes for unsupervised speech pattern discovery is also possible with this corpus, as demonstrated by a preliminary study conducted on a subset of the corpus (10h, 10k spoken captions).

[1]  James R. Glass,et al.  Deep multimodal semantic embeddings for speech and images , 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

[2]  D. Schwarz,et al.  Corpus-Based Concatenative Synthesis , 2007, IEEE Signal Processing Magazine.

[3]  Qi Wu,et al.  Visual question answering: A survey of methods and datasets , 2016, Comput. Vis. Image Underst..

[4]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[5]  Aren Jansen,et al.  Efficient spoken term discovery using randomized algorithms , 2011, 2011 IEEE Workshop on Automatic Speech Recognition & Understanding.

[6]  Yin Li,et al.  Learning Deep Structure-Preserving Image-Text Embeddings , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Yoshua Bengio,et al.  Attention-Based Models for Speech Recognition , 2015, NIPS.

[8]  Peter Young,et al.  From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions , 2014, TACL.

[9]  Grzegorz Chrupala,et al.  Representations of language in a model of visually grounded speech signal , 2017, ACL.

[10]  Fei-Fei Li,et al.  Deep visual-semantic alignments for generating image descriptions , 2015, CVPR.

[11]  Nazli Ikizler-Cinbis,et al.  Automatic Description Generation from Images: A Survey of Models, Datasets, and Evaluation Measures , 2016, J. Artif. Intell. Res..

[12]  Gregory Shakhnarovich,et al.  Visually Grounded Learning of Keyword Prediction from Untranscribed Speech , 2017, INTERSPEECH.

[13]  Michael S. Bernstein,et al.  Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations , 2016, International Journal of Computer Vision.

[14]  S. Brennan,et al.  Disfluency Rates in Conversation: Effects of Age, Relationship, Topic, Role, and Gender , 2001, Language and speech.

[15]  Deb Roy,et al.  Grounded spoken language acquisition: experiments in word learning , 2003, IEEE Trans. Multim..

[16]  Xinlei Chen,et al.  Microsoft COCO Captions: Data Collection and Evaluation Server , 2015, ArXiv.

[17]  Peter Young,et al.  Framing Image Description as a Ranking Task: Data, Models and Evaluation Metrics , 2013, J. Artif. Intell. Res..

[18]  Bogdan Ludusan,et al.  Bridging the gap between speech technology and natural language processing: an evaluation toolbox for term discovery systems , 2014, LREC.

[19]  Nobuyuki Shimizu,et al.  Cross-Lingual Image Caption Generation , 2016, ACL.

[20]  James R. Glass,et al.  Learning Word-Like Units from Joint Audio-Visual Analysis , 2017, ACL.