English
Related papers

Related papers: T5Gemma-TTS Technical Report

200 papers

Current language models (LMs) use a fixed, static subword tokenizer. This default choice typically results in degraded efficiency and language capabilities, especially in languages other than English. To address this issue, we challenge the…

Computation and Language · Computer Science 2025-06-12 Darius Feher , Ivan Vulić , Benjamin Minixhofer

Benefiting from the development of deep learning, text-to-speech (TTS) techniques using clean speech have achieved significant performance improvements. The data collected from real scenes often contains noise and generally needs to be…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-06 Qiushi Zhu , Yu Gu , Rilin Chen , Chao Weng , Yuchen Hu , Lirong Dai , Jie Zhang

Frozen encoder--decoder language models are stateless: the latent representation is discarded after every forward pass, so no information persists across sessions. This paper presents a \textbf{proof-of-concept pilot study} showing that…

Machine Learning · Computer Science 2026-03-18 Hong Jeong

We investigate multi-stage pretraining for prosody modeling in diffusion-based TTS. A speaker-conditioned dual-stream encoder is trained with masked language modeling followed by SigLIP-style cross-modal contrastive learning using…

Large Language Models (LLMs) have demonstrated impressive performance on multiple-choice question answering (MCQA) benchmarks, yet they remain highly vulnerable to minor input perturbations. In this paper, we introduce and evaluate Token…

Computation and Language · Computer Science 2025-06-12 Jui-Ming Yao , Hao-Yuan Chen , Zi-Xian Tang , Bing-Jia Tan , Sheng-Wei Peng , Bing-Cheng Xie , Shun-Feng Su

This paper aims to enhance low-resource TTS by reducing training data requirements using compact speech representations. A Multi-Stage Multi-Codebook (MSMC) VQ-GAN is trained to learn the representation, MSMCR, and decode it to waveforms.…

Sound · Computer Science 2022-10-28 Haohan Guo , Fenglong Xie , Xixin Wu , Hui Lu , Helen Meng

Audio Language Models (ALM) have emerged as the dominant paradigm for speech and music generation by representing audio as sequences of discrete tokens. Yet, unlike text tokens, which are invertible, audio tokens are extracted from lossy…

Sound · Computer Science 2026-01-14 Simon Rouard , Manu Orsini , Axel Roebel , Neil Zeghidour , Alexandre Défossez

While neural methods for text-to-speech (TTS) have shown great advances in modeling multiple speakers, even in zero-shot settings, the amount of data needed for those approaches is generally not feasible for the vast majority of the world's…

Computation and Language · Computer Science 2022-10-25 Florian Lux , Julia Koch , Ngoc Thang Vu

Text-to-speech (TTS) methods have shown promising results in voice cloning, but they require a large number of labeled text-speech pairs. Minimally-supervised speech synthesis decouples TTS by combining two types of discrete speech…

Sound · Computer Science 2023-12-19 Chunyu Qiang , Hao Li , Yixin Tian , Yi Zhao , Ying Zhang , Longbiao Wang , Jianwu Dang

Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potential for zero-shot cross-lingual transfer. However, these multilingual encoders do not precisely align words and phrases across languages.…

Computation and Language · Computer Science 2021-09-13 Kuan-Hao Huang , Wasi Uddin Ahmad , Nanyun Peng , Kai-Wei Chang

As the character-based end-to-end automatic speech recognition (ASR) models evolve, the choice of acoustic modeling units becomes important. Since Korean is a fairly phonetic language and has a unique writing system with its own Korean…

Sound · Computer Science 2019-10-28 Jisung Wang , Jihwan Kim , Sangki Kim , Yeha Lee

This study proposes a segmental-level prosodic probing framework to evaluate neural TTS models' ability to reproduce consonant-induced f0 perturbation, a fine-grained segmental-prosodic effect that reflects local articulatory mechanisms. We…

Computation and Language · Computer Science 2026-03-24 Tianle Yang , Chengzhe Sun , Phil Rose , Cassandra L. Jacobs , Siwei Lyu

Most text-to-speech (TTS) methods use high-quality speech corpora recorded in a well-designed environment, incurring a high cost for data collection. To solve this problem, existing noise-robust TTS methods are intended to use noisy speech…

Sound · Computer Science 2022-06-30 Takaaki Saeki , Kentaro Tachibana , Ryuichi Yamamoto

We propose a multitask training method for attention-based end-to-end speech recognition models. We regularize the decoder in a listen, attend, and spell model by multitask training it on both audio-text and text-only data. Trained on the…

Computation and Language · Computer Science 2021-06-15 Peidong Wang , Tara N. Sainath , Ron J. Weiss

Recently, there has been a growing interest in text-to-speech (TTS) methods that can be trained with minimal supervision by combining two types of discrete speech representations and using two sequence-to-sequence tasks to decouple TTS.…

Sound · Computer Science 2023-12-19 Chunyu Qiang , Hao Li , Hao Ni , He Qu , Ruibo Fu , Tao Wang , Longbiao Wang , Jianwu Dang

Recently, pre-trained models with phonetic supervision have demonstrated their advantages for crosslingual speech recognition in data efficiency and information sharing across languages. However, a limitation is that a pronunciation lexicon…

Audio and Speech Processing · Electrical Eng. & Systems 2025-12-17 Saierdaer Yusuyin , Te Ma , Hao Huang , Zhijian Ou

Standard-to-dialect machine translation remains challenging due to a persistent dialect gap in large language models and evaluation distortions inherent in n-gram metrics, which favor source copying over authentic dialect translation. In…

Computation and Language · Computer Science 2026-03-18 Keunhyeung Park , Seunguk Yu , Youngbin Kim

Non-autoregressive translation (NAT) models, which remove the dependence on previous target tokens from the inputs of the decoder, achieve significantly inference speedup but at the cost of inferior accuracy compared to autoregressive…

Computation and Language · Computer Science 2018-12-27 Junliang Guo , Xu Tan , Di He , Tao Qin , Linli Xu , Tie-Yan Liu

Pause insertion, also known as phrase break prediction and phrasing, is an essential part of TTS systems because proper pauses with natural duration significantly enhance the rhythm and intelligibility of synthetic speech. However,…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-28 Dong Yang , Tomoki Koriyama , Yuki Saito , Takaaki Saeki , Detai Xin , Hiroshi Saruwatari

Transformer-based end-to-end speech recognition models have received considerable attention in recent years due to their high training speed and ability to model a long-range global context. Position embedding in the transformer…

Sound · Computer Science 2021-07-14 Shengqiang Li , Menglong Xu , Xiao-Lei Zhang