Benchmarking Prosody Encoding in Discrete Speech Tokens

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Onda, Kentaro, Fukayama, Satoru, Saito, Daisuke, Minematsu, Nobuaki
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913993224880128
author Onda, Kentaro
Fukayama, Satoru
Saito, Daisuke
Minematsu, Nobuaki
author_facet Onda, Kentaro
Fukayama, Satoru
Saito, Daisuke
Minematsu, Nobuaki
contents Recently, discrete tokens derived from self-supervised learning (SSL) models via k-means clustering have been actively studied as pseudo-text in speech language models and as efficient intermediate representations for various tasks. However, these discrete tokens are typically learned in advance, separately from the training of language models or downstream tasks. As a result, choices related to discretization, such as the SSL model used or the number of clusters, must be made heuristically. In particular, speech language models are expected to understand and generate responses that reflect not only the semantic content but also prosodic features. Yet, there has been limited research on the ability of discrete tokens to capture prosodic information. To address this gap, this study conducts a comprehensive analysis focusing on prosodic encoding based on their sensitivity to the artificially modified prosody, aiming to provide practical guidelines for designing discrete tokens.
format Preprint
id arxiv_https___arxiv_org_abs_2508_11224
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Benchmarking Prosody Encoding in Discrete Speech Tokens
Onda, Kentaro
Fukayama, Satoru
Saito, Daisuke
Minematsu, Nobuaki
Sound
Computation and Language
Audio and Speech Processing
Recently, discrete tokens derived from self-supervised learning (SSL) models via k-means clustering have been actively studied as pseudo-text in speech language models and as efficient intermediate representations for various tasks. However, these discrete tokens are typically learned in advance, separately from the training of language models or downstream tasks. As a result, choices related to discretization, such as the SSL model used or the number of clusters, must be made heuristically. In particular, speech language models are expected to understand and generate responses that reflect not only the semantic content but also prosodic features. Yet, there has been limited research on the ability of discrete tokens to capture prosodic information. To address this gap, this study conducts a comprehensive analysis focusing on prosodic encoding based on their sensitivity to the artificially modified prosody, aiming to provide practical guidelines for designing discrete tokens.
title Benchmarking Prosody Encoding in Discrete Speech Tokens
topic Sound
Computation and Language
Audio and Speech Processing
url https://arxiv.org/abs/2508.11224