English
Related papers

Related papers: SUNAC: Source-aware Unified Neural Audio Codec

200 papers

Creating universal speaker encoders which are robust for different acoustic and speech duration conditions is a big challenge today. According to our observations systems trained on short speech segments are optimal for short phrase speaker…

Sound · Computer Science 2022-10-31 Sergey Novoselov , Vladimir Volokhov , Galina Lavrentyeva

This paper introduces an area-based source separation method designed for virtual meeting scenarios. The aim is to preserve speech signals from an unspecified number of sources within a defined spatial area in front of a linear microphone…

Audio and Speech Processing · Electrical Eng. & Systems 2024-08-20 Martin Strauss , Okan Köpüklü

In this paper, we propose a novel joint source-channel coding (JSCC) approach for channel-adaptive digital semantic communications. In semantic communication systems with digital modulation and demodulation, robust design of JSCC encoder…

Signal Processing · Electrical Eng. & Systems 2024-03-19 Joohyuk Park , Yongjeong Oh , Seonjung Kim , Yo-Seb Jeon

We propose FlowDec, a neural full-band audio codec for general audio sampled at 48 kHz that combines non-adversarial codec training with a stochastic postfilter based on a novel conditional flow matching method. Compared to the prior work…

A joint source-channel coding (JSCC) scheme based on hybrid digital/analog coding is proposed for the transmission of correlated sources over discrete-memoryless two-way channels (DM-TWCs). The scheme utilizes the correlation between the…

Information Theory · Computer Science 2020-08-13 Jian-Jia Weng , Fady Alajaji , Tamás Linder

Neural audio codec models are becoming increasingly important as they serve as tokenizers for audio, enabling efficient transmission or facilitating speech language modeling. The ideal neural audio codec should maintain content,…

Audio provides critical situational cues, yet current Audio Language Models (ALMs) face an attention bottleneck in long-form recordings where dominant background patterns can dilute rare, salient events. We introduce NAACA, a training-free…

Sound · Computer Science 2026-05-14 Zhongju Yuan , Geraint Wiggins , Dick Botteldooren

Scalability and efficiency are desired in neural speech codecs, which supports a wide range of bitrates for applications on various devices. We propose a collaborative quantization (CQ) scheme to jointly learn the codebook of LPC…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-14 Kai Zhen , Mi Suk Lee , Jongmo Sung , Seungkwon Beack , Minje Kim

This paper proposes StreamCodec, a streamable neural audio codec designed for real-time communication. StreamCodec adopts a fully causal, symmetric encoder-decoder structure and operates in the modified discrete cosine transform (MDCT)…

Sound · Computer Science 2025-04-10 Xiao-Hang Jiang , Yang Ai , Rui-Chen Zheng , Zhen-Hua Ling

Distributed source coding (DSC) is the task of encoding an input in the absence of correlated side information that is only available to the decoder. Remarkably, Slepian and Wolf showed in 1973 that an encoder without access to the side…

Information Theory · Computer Science 2024-07-02 Jay Whang , Alliot Nagle , Anish Acharya , Hyeji Kim , Alexandros G. Dimakis

We present StreamVC, a streaming voice conversion solution that preserves the content and prosody of any source speech while matching the voice timbre from any target speech. Unlike previous approaches, StreamVC produces the resulting…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-09 Yang Yang , Yury Kartynnik , Yunpeng Li , Jiuqiang Tang , Xing Li , George Sung , Matthias Grundmann

Universal source separation targets at separating the audio sources of an arbitrary mix, removing the constraint to operate on a specific domain like speech or music. Yet, the potential of universal source separation is limited because most…

Sound · Computer Science 2023-10-03 Jordi Pons , Xiaoyu Liu , Santiago Pascual , Joan Serrà

Neural source-filter (NSF) waveform models generate speech waveforms by morphing sine-based source signals through dilated convolution in the time domain. Although the sine-based source signals help the NSF models to produce voiced sounds…

Audio and Speech Processing · Electrical Eng. & Systems 2020-04-13 Xin Wang , Junichi Yamagishi

Neural machine translation (NMT) takes deterministic sequences for source representations. However, either word-level or subword-level segmentations have multiple choices to split a source sequence with different word segmentors or…

Computation and Language · Computer Science 2019-06-05 Fengshun Xiao , Jiangtong Li , Hai Zhao , Rui Wang , Kehai Chen

Due to its rapid response time and a high degree of robustness, the selective fixed-filter active noise control (SFANC) method appears to be a viable candidate for widespread use in a variety of practical active noise control (ANC) systems.…

Machine Learning · Computer Science 2022-08-19 Zhengding Luo , Dongyuan Shi , Woon-Seng Gan

We consider the problem of transmission of several distributed correlated sources over a multiple access channel (MAC) with side information at the sources and the decoder. Source-channel separation does not hold for this channel.…

Information Theory · Computer Science 2016-11-15 R. Rajesh , Vinod Sharma , V. K. Varshenya

Audio source separation is often used as preprocessing of various applications, and one of its ultimate goals is to construct a single versatile model capable of dealing with the varieties of audio signals. Since sampling frequency, one of…

Sound · Computer Science 2021-05-11 Koichi Saito , Tomohiko Nakamura , Kohei Yatabe , Yuma Koizumi , Hiroshi Saruwatari

This paper introduces FlowMAC, a novel neural audio codec for high-quality general audio compression at low bit rates based on conditional flow matching (CFM). FlowMAC jointly learns a mel spectrogram encoder, quantizer and decoder. At…

Audio and Speech Processing · Electrical Eng. & Systems 2025-04-08 Nicola Pia , Martin Strauss , Markus Multrus , Bernd Edler

The state of the art in music source separation employs neural networks trained in a supervised fashion on multi-track databases to estimate the sources from a given mixture. With only few datasets available, often extensive data…

Machine Learning · Computer Science 2018-04-09 Daniel Stoller , Sebastian Ewert , Simon Dixon

Although discrete speech tokens have exhibited strong potential for language model-based speech generation, their high bitrates and redundant timbre information restrict the development of such models. In this work, we propose LSCodec, a…

Audio and Speech Processing · Electrical Eng. & Systems 2025-05-22 Yiwei Guo , Zhihan Li , Chenpeng Du , Hankun Wang , Xie Chen , Kai Yu
‹ Prev 1 8 9 10 Next ›