English
Related papers

Related papers: Real-Time Streaming Mel Vocoding with Generative F…

200 papers

Recently, GAN based speech synthesis methods, such as MelGAN, have become very popular. Compared to conventional autoregressive based methods, parallel structures based generators make waveform generation process fast and stable. However,…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-25 Qiao Tian , Yi Chen , Zewang Zhang , Heng Lu , Linghui Chen , Lei Xie , Shan Liu

Ultra-low-bitrate speech coding is pivotal for bandwidth-constrained communication and deep compression, yet maintaining naturalness and speaker identity at such extreme bit budgets remains challenging due to pronounced information loss and…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-26 Hui-Peng Du , Yang Ai , Xiao-Hang Jiang , Yuan Tian , Zhen-Hua Ling

The mainstream neural text-to-speech(TTS) pipeline is a cascade system, including an acoustic model(AM) that predicts acoustic feature from the input transcript and a vocoder that generates waveform according to the given acoustic feature.…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-25 Chenpeng Du , Yiwei Guo , Xie Chen , Kai Yu

In a recent paper, we have presented a generative adversarial network (GAN)-based model for unconditional generation of the mel-spectrograms of singing voices. As the generator of the model is designed to take a variable-length sequence of…

Audio and Speech Processing · Electrical Eng. & Systems 2021-05-13 Jen-Yu Liu , Yu-Hua Chen , Yin-Cheng Yeh , Yi-Hsuan Yang

Neural audio codecs are a fundamental component of modern generative audio pipelines. Although recent codecs achieve strong low-bitrate reconstruction and provide powerful representations for downstream tasks, most are non-streamable,…

Sound · Computer Science 2025-09-22 Luca Della Libera , Cem Subakan , Mirco Ravanelli

We introduce RapFlow-TTS, a rapid and high-fidelity TTS acoustic model that leverages velocity consistency constraints in flow matching (FM) training. Although ordinary differential equation (ODE)-based TTS generation achieves…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-23 Hyun Joon Park , Jeongmin Liu , Jin Sob Kim , Jeong Yeol Yang , Sung Won Han , Eunwoo Song

In this paper, a neural network named Sequence-to-sequence ConvErsion NeTwork (SCENT) is presented for acoustic modeling in voice conversion. At training stage, a SCENT model is estimated by aligning the feature sequences of source and…

Sound · Computer Science 2020-01-14 Jing-Xuan Zhang , Zhen-Hua Ling , Li-Juan Liu , Yuan Jiang , Li-Rong Dai

Recently sequence-to-sequence models have started to achieve state-of-the-art performance on standard speech recognition tasks when processing audio data in batch mode, i.e., the complete audio data is available when starting processing.…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-28 Thai-Son Nguyen , Ngoc-Quan Pham , Sebastian Stueker , Alex Waibel

Recent advancements in generative modeling have significantly enhanced the reconstruction of audio waveforms from various representations. While diffusion models are adept at this task, they are hindered by latency issues due to their…

Sound · Computer Science 2024-10-08 Peng Liu , Dongyang Dai , Zhiyong Wu

Recent development of neural vocoders based on the generative adversarial neural network (GAN) has shown obvious advantages of generating raw waveform conditioned on mel-spectrogram with fast inference speed and lightweight networks.…

Sound · Computer Science 2023-05-30 Kun Song , Yongmao Zhang , Yi Lei , Jian Cong , Hanzhao Li , Lei Xie , Gang He , Jinfeng Bai

This paper presents an end-to-end text-to-speech system with low latency on a CPU, suitable for real-time applications. The system is composed of an autoregressive attention-based sequence-to-sequence acoustic model and the LPCNet vocoder…

We present two methods of real time magnitude spectrogram inversion: streaming Griffin Lim(GL) and streaming MelGAN. We demonstrate the impact of looking ahead on perceptual quality of MelGAN. As little as one hop size (12.5ms) of lookahead…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-26 Oleg Rybakov , Marco Tagliasacchi , Yunpeng Li , Liyang Jiang , Xia Zhang , Fadi Biadsy

Speech Enhancement techniques have become core technologies in mobile devices and voice software. Still, modern deep learning solutions often require high amount of computational resources what makes their usage on low-resource devices…

Sound · Computer Science 2025-07-24 Ekaterina Dmitrieva , Maksim Kaledin

Recent approaches in text-to-speech (TTS) synthesis employ neural network strategies to vocode perceptually-informed spectrogram representations directly into listenable waveforms. Such vocoding procedures create a computational bottleneck…

Sound · Computer Science 2019-07-29 Paarth Neekhara , Chris Donahue , Miller Puckette , Shlomo Dubnov , Julian McAuley

In this paper, we introduce V2SFlow, a novel Video-to-Speech (V2S) framework designed to generate natural and intelligible speech directly from silent talking face videos. While recent V2S systems have shown promising results on constrained…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Jeongsoo Choi , Ji-Hoon Kim , Jinyu Li , Joon Son Chung , Shujie Liu

Real-time LLM interactions demand streamed token generations, where text tokens are progressively generated and delivered to users while balancing two objectives: responsiveness (i.e., low time-to-first-token) and steady generation…

Machine Learning · Computer Science 2025-10-06 Junyi Chen , Chuheng Du , Renyuan Liu , Shuochao Yao , Dingtian Yan , Jiang Liao , Shengzhong Liu , Fan Wu , Guihai Chen

State of the art (SOTA) neural text to speech (TTS) models can generate natural-sounding synthetic voices. These models are characterized by large memory footprints and substantial number of operations due to the long-standing focus on…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-24 Rowel Atienza

Large Language Models (LLMs) demonstrate impressive capabilities, yet interaction with these models is mostly facilitated through text. Using Text-To-Speech to synthesize LLM outputs typically results in notable latency, which is…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-21 Avihu Dekel , Slava Shechtman , Raul Fernandez , David Haws , Zvi Kons , Ron Hoory

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

Gaps, dropouts and short clips of corrupted audio are a common problem and particularly annoying when they occur in speech. This paper uses machine learning to regenerate gaps of up to 320ms in an audio speech signal. Audio regeneration is…

Sound · Computer Science 2023-05-11 Deniss Strods , Alan F. Smeaton