Search Results for author: Simon Durand

Found 5 papers, 4 papers with code

LLark: A Multimodal Instruction-Following Language Model for Music

2 code implementations11 Oct 2023 Josh Gardner, Simon Durand, Daniel Stoller, Rachel M. Bittner

Music has a unique and complex structure which is challenging for both expert humans and existing AI systems to understand, and presents unique challenges relative to other forms of audio.

Instruction Following Language Modelling

Contrastive Learning-Based Audio to Lyrics Alignment for Multiple Languages

1 code implementation13 Jun 2023 Simon Durand, Daniel Stoller, Sebastian Ewert

This way, we obtain a novel system that is simple to train end-to-end, can make use of weakly annotated training data, jointly learns a powerful text model, and is tailored to alignment.

Contrastive Learning speech-recognition +1

Data Cleansing with Contrastive Learning for Vocal Note Event Annotations

1 code implementation5 Aug 2020 Gabriel Meseguer-Brocal, Rachel Bittner, Simon Durand, Brian Brost

We propose a novel data cleansing model for time-varying, structured labels which exploits the local structure of the labels, and demonstrate its usefulness for vocal note event annotations in music.

Contrastive Learning Information Retrieval +2

Dereverberation using joint estimation of dry speech signal and acoustic system

no code implementations24 Jul 2020 Sanna Wager, Keunwoo Choi, Simon Durand

The purpose of speech dereverberation is to remove quality-degrading effects of a time-invariant impulse response filter from the signal.

Room Impulse Response (RIR) Speech Dereverberation

End-to-end Lyrics Alignment for Polyphonic Music Using an Audio-to-Character Recognition Model

2 code implementations18 Feb 2019 Daniel Stoller, Simon Durand, Sebastian Ewert

Time-aligned lyrics can enrich the music listening experience by enabling karaoke, text-based song retrieval and intra-song navigation, and other applications.

Retrieval

Cannot find the paper you are looking for? You can Submit a new open access paper.