English
Related papers

Related papers: Koel-TTS: Enhancing LLM based Speech Generation wi…

200 papers

Practicing conversations with large language models (LLMs) presents a promising alternative to traditional in-person language learning. However, most LLMs generate text at a near-native level of complexity, making them ill-suited for first…

Computation and Language · Computer Science 2026-02-19 Meiqing Jin , Liam Dugan , Chris Callison-Burch

Text-to-Speech (TTS) models can generate natural, human-like speech across multiple languages by transforming phonemes into waveforms. However, multilingual TTS remains challenging due to discrepancies in phoneme vocabularies and variations…

Sound · Computer Science 2025-04-14 Haowei Lou , Hye-young Paik , Sheng Li , Wen Hu , Lina Yao

Artificial speech synthesis has made a great leap in terms of naturalness as recent Text-to-Speech (TTS) systems are capable of producing speech with similar quality to human recordings. However, not all speaking styles are easy to model:…

Recent advancements in text-to-speech (TTS) have shown that language model (LM) based systems offer competitive performance compared to traditional approaches. However, in training, TTS models use ground-truth (GT) tokens as prefixes to…

Sound · Computer Science 2025-09-23 Ruonan Zhang , Lingzhou Mu , Xixin Wu , Kai Zhang

We present MELLE, a novel continuous-valued token based language modeling approach for text-to-speech synthesis (TTS). MELLE autoregressively generates continuous mel-spectrogram frames directly from text condition, bypassing the need for…

Computation and Language · Computer Science 2025-05-28 Lingwei Meng , Long Zhou , Shujie Liu , Sanyuan Chen , Bing Han , Shujie Hu , Yanqing Liu , Jinyu Li , Sheng Zhao , Xixin Wu , Helen Meng , Furu Wei

Text-to-Speech (TTS) has recently seen great progress in synthesizing high-quality speech owing to the rapid development of parallel TTS systems, but producing speech with naturalistic prosodic variations, speaking styles and emotional…

Audio and Speech Processing · Electrical Eng. & Systems 2023-11-21 Yinghao Aaron Li , Cong Han , Nima Mesgarani

Recent years have witnessed a trend that large language model (LLM) based text-to-speech (TTS) emerges into the mainstream due to their high naturalness and zero-shot capacity. In this paradigm, speech signals are discretized into token…

Recently, text-to-speech (TTS) models such as FastSpeech and ParaNet have been proposed to generate mel-spectrograms from text in parallel. Despite the advantage, the parallel TTS models cannot be trained without guidance from…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-26 Jaehyeon Kim , Sungwon Kim , Jungil Kong , Sungroh Yoon

Current text to speech (TTS) systems usually leverage a cascaded acoustic model and vocoder pipeline with mel-spectrograms as the intermediate representations, which suffer from two limitations: 1) the acoustic model and vocoder are…

Sound · Computer Science 2022-07-12 Yanqing Liu , Ruiqing Xue , Lei He , Xu Tan , Sheng Zhao

Several recent end-to-end text-to-speech (TTS) models enabling single-stage training and parallel sampling have been proposed, but their sample quality does not match that of two-stage TTS systems. In this work, we present a parallel…

Sound · Computer Science 2021-06-14 Jaehyeon Kim , Jungil Kong , Juhee Son

This technical report presents MOSS-TTS, a speech generation foundation model built on a scalable recipe: discrete audio tokens, autoregressive modeling, and large-scale pretraining. Built on MOSS-Audio-Tokenizer, a causal Transformer…

Recent advances in large language models (LLMs) and development of audio codecs greatly propel the zero-shot TTS. They can synthesize personalized speech with only a 3-second speech of an unseen speaker as acoustic prompt. However, they…

Sound · Computer Science 2024-06-07 Jinlong Xue , Yayue Deng , Yicheng Han , Yingming Gao , Ya Li

Currently, many multi-speaker speech synthesis and voice conversion systems address speaker variations with an embedding vector. Modeling it directly allows new voices outside of training data to be synthesized. GMM based approaches such as…

Sound · Computer Science 2023-09-26 Yao Shi , Ming Li

Recent prompt-based text-to-speech (TTS) models can clone an unseen speaker using only a short speech prompt. They leverage a strong in-context ability to mimic the speech prompts, including speaker style, prosody, and emotion. Therefore,…

Sound · Computer Science 2024-06-07 Jinlong Xue , Yayue Deng , Yingming Gao , Ya Li

Speech-language models (SLMs) offer a promising path toward unifying speech and text understanding and generation. However, challenges remain in achieving effective cross-modal alignment and high-quality speech generation. In this work, we…

Scaling text-to-speech (TTS) with autoregressive language model (LM) to large-scale datasets by quantizing waveform into discrete speech tokens is making great progress to capture the diversity and expressiveness in human speech, but the…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-10 Chong Zhang , Yanqing Liu , Yang Zheng , Sheng Zhao

The rapid development of neural text-to-speech (TTS) systems enabled its usage in other areas of natural language processing such as automatic speech recognition (ASR) or spoken language translation (SLT). Due to the large number of…

Computation and Language · Computer Science 2024-08-01 Nick Rossenbach , Ralf Schlüter , Sakriani Sakti

Modern Text-to-Speech (TTS) systems increasingly leverage Large Language Model (LLM) architectures to achieve scalable, high-fidelity, zero-shot generation. However, these systems typically rely on fixed-frame-rate acoustic tokenization,…

Expressive text-to-speech (TTS) aims to synthesize speeches with human-like tones, moods, or even artistic attributes. Recent advancements in expressive TTS empower users with the ability to directly control synthesis style through natural…

Audio and Speech Processing · Electrical Eng. & Systems 2023-11-03 Hanglei Zhang , Yiwei Guo , Sen Liu , Xie Chen , Kai Yu

Language Model (LM)-based generative modeling has emerged as a promising direction for TSE, offering potential for improved generalization and high-fidelity speech. We present GenTSE, a two-stage decoder-only generative LM approach for TSE:…

Audio and Speech Processing · Electrical Eng. & Systems 2025-12-25 Haoyang Li , Xuyi Zhuang , Azmat Adnan , Ye Ni , Wei Rao , Shreyas Gopal , Eng Siong Chng