Congratulations to Md Iftekhar Tanveer, Diego Casabuena, and @jussikarlgren and Rosie Jones on their paper on Unsupervised Speaker Diarization that is Agnostic to Language Overlap Aware and Free of Tuning appearing at #interspeech2022

Congratulations to Katariina Martikainen, @jussikarlgren and Khiet Truong on their paper Exploring Audio-based Stylistic Variation in Podcasts appearing at #interspeech2022

More research scientist summer internships have opened up Spotify Research, in NLP and audio understanding. Applications close February 8th lifeatspotify.com/jobs/summer-in…

We are delighted to announce our recent paper accepted at #Interspeech2023: “Lightweight and Efficient Spoken Language Identification of Long-form Audio”. The paper focuses on efficient solution for detecting languages in talk audio contents like podcasts.

Our paper "Lightweight and Efficient Spoken Language Identification of Long-form Audio" is accepted at #INTERSPEECH2023. It proposed a system to detect spoken language in long audio with multiple speakers, enabling utterance-level inference and code-switching detection.