TTS-Transducer: End-to-End Speech Synthesis with Neural Transducer

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3A2EC93SW8" target="_blank" >RIV/00216208:11320/26:2EC93SW8 - isvavai.cz</a>

Result on the web

<a href="https://ieeexplore.ieee.org/abstract/document/10890256" target="_blank" >https://ieeexplore.ieee.org/abstract/document/10890256</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICASSP49660.2025.10890256" target="_blank" >10.1109/ICASSP49660.2025.10890256</a>

Result language

angličtina

Original language name

TTS-Transducer: End-to-End Speech Synthesis with Neural Transducer

Original language description

This work introduces TTS-Transducer – a novel architecture for text-to-speech, leveraging the strengths of audio codec models and neural transducers. Transducers, renowned for their superior quality and robustness in speech recognition, are employed to learn monotonic alignments and allow for avoiding using explicit duration predictors. Neural audio codecs efficiently compress audio into discrete codes, revealing the possibility of applying text modeling approaches to speech generation. However, the complexity of predicting multiple tokens per frame from several codebooks, as necessitated by audio codec models with residual quantizers, poses a significant challenge. The proposed system first uses a transducer architecture to learn monotonic alignments between tokenized text and speech codec tokens for the first codebook. Next, a non-autoregressive Transformer predicts the remaining codes using the alignment extracted from transducer loss. The proposed system is trained end-to-end. We show that TTS-Transducer is a competitive and robust alternative to contemporary TTS systems1.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

—

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

ISBN

—

ISSN

15206149

e-ISSN

—

Number of pages

5

Pages from-to

1-5

Publisher name

—

Place of publication

—

Event location

Hyderabad

Event date

Jan 1, 2026

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—