paper-with-me

홈 › Papers

How Should We Extract Discrete Audio Tokens from Self-Supervised Models?

2024-06-15 · Pooneh Mousavi, Jarod Duret, Salah Zaiem, Luca Della Libera, Artem Ploujnikov, Cem Subakan, Mirco Ravanelli

Discrete audio tokens have recently gained attention for their potential to bridge the gap between audio and language processing. Ideal audio tokens must preserve content, paralinguistic elements, speaker identity, and many other audio details. Current audio tokenization methods fall into two categories: Semantic tokens, acquired through quantization of Self-Supervised Learning (SSL) models, and Neural compression-based tokens (codecs). Although previous studies have benchmarked codec models to identify optimal configurations, the ideal setup for quantizing pretrained SSL models remains unclear. This paper explores the optimal configuration of semantic tokens across discriminative and generative tasks. We propose a scalable solution to train a universal vocoder across multiple SSL layers. Furthermore, an attention mechanism is employed to identify task-specific influential layers, enhancing the adaptability and performance of semantic tokens in diverse audio applications.

📄 PDF Abstract BibTeX arXiv:2406.10735

Code (0)

등록된 구현이 없습니다.

Tasks

QuantizationSelf-Supervised Learning

Similar Papers 제목 키워드 기반

CLAP-ART: Automated Audio Captioning with Semantic-rich Audio Representation Tokenizer

2025-06-01 · Daiki Takeuchi, Binh Thien Nguyen, Masahiro Yasuda, Yasunori Ohishi 외

Automated Audio Captioning (AAC) aims to describe the semantic contexts of general sounds, including acoustic events and scenes, by leveraging effective acoustic features. To enhance performance, an AAC method, EnCLAP, e…

Audio captioningLanguage ModelingLanguage ModellingQuantization

A vector quantized masked autoencoder for audiovisual speech emotion recognition

2023-05-05 · Samir Sadok, Simon Leglaive, Renaud Séguier

An important challenge in emotion recognition is to develop methods that can leverage unlabeled training data. In this paper, we propose the VQ-MAE-AV model, a self-supervised multimodal model that leverages masked autoe…

Contrastive LearningEmotion RecognitionRepresentation LearningSelf-Supervised Learning+1

TSELM: Target Speaker Extraction using Discrete Tokens and Language Models

2024-09-12 · Beilong Tang, Bang Zeng, Ming Li

We propose TSELM, a novel target speaker extraction network that leverages discrete tokens and language models. TSELM utilizes multiple discretized layers from WavLM as input tokens and incorporates cross-attention mecha…

Audio GenerationTarget Speaker Extraction

DASB -- Discrete Audio and Speech Benchmark

2024-06-20 · Pooneh Mousavi, Luca Della Libera, Jarod Duret, Artem Ploujnikov 외

Discrete audio tokens have recently gained considerable attention for their potential to connect audio and language processing, enabling the creation of modern multimodal large language models. Ideal audio tokens must ef…

BenchmarkingEmotion Recognitionintent-classificationIntent Classification+7

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens

2026-07-28 · Daigo Takizawa, Tomohiko Nakamura, Samuele Cornell, William Chen 외 arxiv

Neural audio codecs (NACs) have become popular for obtaining speech representations as discrete tokens. Beyond compression, discrete tokens can be used to train self-supervised learning (SSL) models. Such models, referre…

Self-Supervised Learning