DM-Codec: Distilling Multimodal Representations for Speech Tokenization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ahasan, Md Mubtasim, Fahim, Md, Mohiuddin, Tasnim, Rahman, A K M Mahbubur, Chadha, Aman, Iqbal, Tariq, Amin, M Ashraful, Islam, Md Mofijul, Ali, Amin Ahsan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914063151267840
author Ahasan, Md Mubtasim
Fahim, Md
Mohiuddin, Tasnim
Rahman, A K M Mahbubur
Chadha, Aman
Iqbal, Tariq
Amin, M Ashraful
Islam, Md Mofijul
Ali, Amin Ahsan
author_facet Ahasan, Md Mubtasim
Fahim, Md
Mohiuddin, Tasnim
Rahman, A K M Mahbubur
Chadha, Aman
Iqbal, Tariq
Amin, M Ashraful
Islam, Md Mofijul
Ali, Amin Ahsan
contents Recent advancements in speech-language models have yielded significant improvements in speech tokenization and synthesis. However, effectively mapping the complex, multidimensional attributes of speech into discrete tokens remains challenging. This process demands acoustic, semantic, and contextual information for precise speech representations. Existing speech representations generally fall into two categories: acoustic tokens from audio codecs and semantic tokens from speech self-supervised learning models. Although recent efforts have unified acoustic and semantic tokens for improved performance, they overlook the crucial role of contextual representation in comprehensive speech modeling. Our empirical investigations reveal that the absence of contextual representations results in elevated Word Error Rate (WER) and Word Information Lost (WIL) scores in speech transcriptions. To address these limitations, we propose two novel distillation approaches: (1) a language model (LM)-guided distillation method that incorporates contextual information, and (2) a combined LM and self-supervised speech model (SM)-guided distillation technique that effectively distills multimodal representations (acoustic, semantic, and contextual) into a comprehensive speech tokenizer, termed DM-Codec. The DM-Codec architecture adopts a streamlined encoder-decoder framework with a Residual Vector Quantizer (RVQ) and incorporates the LM and SM during the training process. Experiments show DM-Codec significantly outperforms state-of-the-art speech tokenization models, reducing WER by up to 13.46%, WIL by 9.82%, and improving speech quality by 5.84% and intelligibility by 1.85% on the LibriSpeech benchmark dataset. Code, samples, and checkpoints are available at https://github.com/mubtasimahasan/DM-Codec.
format Preprint
id arxiv_https___arxiv_org_abs_2410_15017
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DM-Codec: Distilling Multimodal Representations for Speech Tokenization
Ahasan, Md Mubtasim
Fahim, Md
Mohiuddin, Tasnim
Rahman, A K M Mahbubur
Chadha, Aman
Iqbal, Tariq
Amin, M Ashraful
Islam, Md Mofijul
Ali, Amin Ahsan
Computation and Language
Artificial Intelligence
Sound
Audio and Speech Processing
Recent advancements in speech-language models have yielded significant improvements in speech tokenization and synthesis. However, effectively mapping the complex, multidimensional attributes of speech into discrete tokens remains challenging. This process demands acoustic, semantic, and contextual information for precise speech representations. Existing speech representations generally fall into two categories: acoustic tokens from audio codecs and semantic tokens from speech self-supervised learning models. Although recent efforts have unified acoustic and semantic tokens for improved performance, they overlook the crucial role of contextual representation in comprehensive speech modeling. Our empirical investigations reveal that the absence of contextual representations results in elevated Word Error Rate (WER) and Word Information Lost (WIL) scores in speech transcriptions. To address these limitations, we propose two novel distillation approaches: (1) a language model (LM)-guided distillation method that incorporates contextual information, and (2) a combined LM and self-supervised speech model (SM)-guided distillation technique that effectively distills multimodal representations (acoustic, semantic, and contextual) into a comprehensive speech tokenizer, termed DM-Codec. The DM-Codec architecture adopts a streamlined encoder-decoder framework with a Residual Vector Quantizer (RVQ) and incorporates the LM and SM during the training process. Experiments show DM-Codec significantly outperforms state-of-the-art speech tokenization models, reducing WER by up to 13.46%, WIL by 9.82%, and improving speech quality by 5.84% and intelligibility by 1.85% on the LibriSpeech benchmark dataset. Code, samples, and checkpoints are available at https://github.com/mubtasimahasan/DM-Codec.
title DM-Codec: Distilling Multimodal Representations for Speech Tokenization
topic Computation and Language
Artificial Intelligence
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2410.15017