DC-Spin: A Speaker-invariant Speech Tokenizer for Spoken Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chang, Heng-Jui, Gong, Hongyu, Wang, Changhan, Glass, James, Chung, Yu-An
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929570606743552
author Chang, Heng-Jui
Gong, Hongyu
Wang, Changhan
Glass, James
Chung, Yu-An
author_facet Chang, Heng-Jui
Gong, Hongyu
Wang, Changhan
Glass, James
Chung, Yu-An
contents Spoken language models (SLMs) have gained increasing attention with advancements in text-based, decoder-only language models. SLMs process text and speech, enabling simultaneous speech understanding and generation. This paper presents Double-Codebook Speaker-invariant Clustering (DC-Spin), which aims to improve speech tokenization by bridging audio signals and SLM tokens. DC-Spin extracts speaker-invariant tokens rich in phonetic information and resilient to input variations, enhancing zero-shot SLM tasks and speech resynthesis. We propose a chunk-wise approach to enable streamable DC-Spin without retraining and degradation. Comparisons of tokenization methods (self-supervised and neural audio codecs), model scalability, and downstream task proxies show that tokens easily modeled by an n-gram LM or aligned with phonemes offer strong performance, providing insights for designing speech tokenizers for SLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2410_24177
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DC-Spin: A Speaker-invariant Speech Tokenizer for Spoken Language Models
Chang, Heng-Jui
Gong, Hongyu
Wang, Changhan
Glass, James
Chung, Yu-An
Audio and Speech Processing
Computation and Language
Machine Learning
Sound
Spoken language models (SLMs) have gained increasing attention with advancements in text-based, decoder-only language models. SLMs process text and speech, enabling simultaneous speech understanding and generation. This paper presents Double-Codebook Speaker-invariant Clustering (DC-Spin), which aims to improve speech tokenization by bridging audio signals and SLM tokens. DC-Spin extracts speaker-invariant tokens rich in phonetic information and resilient to input variations, enhancing zero-shot SLM tasks and speech resynthesis. We propose a chunk-wise approach to enable streamable DC-Spin without retraining and degradation. Comparisons of tokenization methods (self-supervised and neural audio codecs), model scalability, and downstream task proxies show that tokens easily modeled by an n-gram LM or aligned with phonemes offer strong performance, providing insights for designing speech tokenizers for SLMs.
title DC-Spin: A Speaker-invariant Speech Tokenizer for Spoken Language Models
topic Audio and Speech Processing
Computation and Language
Machine Learning
Sound
url https://arxiv.org/abs/2410.24177