Deep Learning

Ridi, Pagliaccio !

Neural style transfer for videos.

The contribution of lip protrusion to Anglo-English /r/: Evidence from hyper- and non-hyperarticulated speech

Articulatory variation of /r/ has been widely observed in rhotic varieties of English, particularly with regards to tongue body shapes, which range from retroflex to bunched. However, little is known about the production of /r/ in modern non-rhotic …

The contribution of lip protrusion to Anglo-English /r/: Evidence from hyper- and non-hyperarticulated speech

Here in my deep purple dreams

On the deep learning approach to phonetics: black boxes?

Deep learning and voice comparison: phonetically-motivated vs. automatically-learned features

Broadband spectrograms of French vowels /ɑ̃/, /a/, /ɛ/, /e/, /i/, /ə/, and /ɔ/ extracted from radio broadcast corpora were used to recognize 45 speakers with a deep convolutional neural network (CNN). The same network was also trained with 62 …

Towards phonetic interpretability in deep learning applied to voice comparison

A deep convolutional neural network was trained to classify 45 speakers based on spectrograms of their productions of the French vowel /ɑ̃/ Although the model achieved fairly high accuracy – over 85 % – our primary focus here was phonetic …

Labiodentals /r/ here to stay: Deep learning explains why

Articulatory variation has been well-documented in approximant realisations of English /r/. Despite the diversity of tongue shapes [1–3], the acoustic profile of /r/ is relatively stable [4], characterised by a very low F3 [1,5,6] close to F2 [7,8]. However, the production of /r/ remains enigmatic, especially concerning non-rhotic Englishes and the accompanying labial gesture. The lips are particularly pertinent to Anglo-English /r/ because high-F3 labiodental variants are rapidly gaining currency [9,10].

Deep learning and voice comparison : phonetically-motivated vs. automatically-learned features

Towards phonetic interpretability in deep learning applied to voice comparison

VoxCrim

Forensic Voice Comparison