English
Related papers

Related papers: Improving X-Codec-2.0 for Multi-Lingual Speech: 25…

200 papers

The increasing data rates expected to be of the order of Gb/s for future wireless systems directly impact the throughput requirements of the modulation and coding subsystems of the physical layer. In an effort to design a suitable channel…

Hardware Architecture · Computer Science 2015-05-19 Swapnil Mhaske , David Uliana , Hojin Kee , Tai Ly , Ahsan Aziz , Predrag Spasojevic

Audio codecs are a critical component of modern speech generation systems. This paper introduces a low-bitrate, multi-scale residual codec that encodes speech into four distinct streams: semantic, timbre, prosody, and residual. This…

Audio and Speech Processing · Electrical Eng. & Systems 2026-02-25 Jingyu Li , Guangyan Zhang , Zhen Ye , Yiwen Guo

Compressing self-supervised models has become increasingly necessary, as self-supervised models become larger. While previous approaches have primarily focused on compressing the model size, shortening sequences is also effective in…

Computation and Language · Computer Science 2022-10-26 Yen Meng , Hsuan-Jui Chen , Jiatong Shi , Shinji Watanabe , Paola Garcia , Hung-yi Lee , Hao Tang

The performance of speaker verification systems degrades significantly under language mismatch, a critical challenge exacerbated by the field's reliance on English-centric data. To address this, we propose the TidyVoice Challenge for…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-30 Aref Farhadipour , Jan Marquenie , Srikanth Madikeri , Teodora Vukovic , Volker Dellwo , Kathy Reid , Francis M. Tyers , Ingo Siegert , Eleanor Chodroff

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…

State-of-the-art trainable machine translation evaluation metrics like xCOMET achieve high correlation with human judgment but rely on large encoders (up to 10.7B parameters), making them computationally expensive and inaccessible to…

Computation and Language · Computer Science 2024-11-11 Daniil Larionov , Mikhail Seleznyov , Vasiliy Viskov , Alexander Panchenko , Steffen Eger

We propose an approach for cognitive coding of speech by unsupervised extraction of contextual representations in two hierarchical levels of abstraction. Speech attributes such as phoneme identity that last one hundred milliseconds or less…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-11 Reza Lotfidereshgi , Philippe Gournay

The development of neural vocoders (NVs) has resulted in the high-quality and fast generation of waveforms. However, conventional NVs target a single sampling rate and require re-training when applied to different sampling rates. A suitable…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-27 Kentaro Mitsui , Kei Sawada

Speech tokenizers serve as foundational components for speech language models, yet current designs exhibit several limitations, including: 1) dependence on multi-layer residual vector quantization structures or high frame rates, 2) reliance…

Sound · Computer Science 2025-08-26 Yuancheng Wang , Dekun Chen , Xueyao Zhang , Junan Zhang , Jiaqi Li , Zhizheng Wu

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,…

Neural image compression, based on auto-encoders and overfitted representations, relies on a latent representation of the coded signal. This representation needs to be compact and uses low resolution feature maps. In the decoding process,…

Image and Video Processing · Electrical Eng. & Systems 2024-12-02 Pierrick Philippe , Théo Ladune , Gordon Clare , Félix Henry , Théophile Blard , Thomas Leguay

Quantum error correction requires accurate and efficient decoding to optimally suppress errors in the encoded information. For concatenated codes, where one code is embedded within another, optimal decoding can be achieved using a…

Quantum Physics · Physics 2025-05-07 Basudha Srivastava , Yinzi Xiao , Anton Frisk Kockum , Ben Criger , Mats Granath

We present LatinX, a multilingual text-to-speech (TTS) model for cascaded speech-to-speech translation that preserves the source speaker's identity across languages. LatinX is a 12-layer decoder-only Transformer trained in three stages: (i)…

Computation and Language · Computer Science 2025-09-09 Luis Felipe Chary , Miguel Arjona Ramirez

High-fidelity general audio compression at ultra-low bitrates is crucial for applications ranging from low-bandwidth communication to generative audio-language modeling. Traditional audio compression methods and contemporary neural codecs…

Audio and Speech Processing · Electrical Eng. & Systems 2026-02-03 Hao Ma , Ruihao Jing , Shansong Liu , Cheng Gong , Chi Zhang , Xiao-Lei Zhang , Xuelong Li

There are several domains that own corresponding widely used feature extractors, such as ResNet, BERT, and GPT-x. These models are usually pre-trained on large amounts of unlabeled data by self-supervision and can be effectively applied to…

Computation and Language · Computer Science 2021-01-19 Cheng Yi , Jianzhong Wang , Ning Cheng , Shiyu Zhou , Bo Xu

In this paper, we combine two-step knowledge distillation, structured pruning, truncation, and vocabulary trimming for extremely compressing multilingual encoder-only language models for low-resource languages. Our novel approach…

Computation and Language · Computer Science 2025-11-07 Daniil Gurgurov , Michal Gregor , Josef van Genabith , Simon Ostermann

Large language models (LLMs) are evolving from conversational systems into strong reasoners for tasks such as Olympiad mathematics and competitive programming. While scaling parameters and test-time computation has driven progress, a key…

Machine Learning · Computer Science 2025-09-25 Xueliang Zhao , Wei Wu , Jian Guan , Zhuocheng Gong , Lingpeng Kong

Continuous monitoring of bipolar disorder agitation via voice biomarkers requires disentangling stable speaker traits from volatile affective states on resource-constrained edge devices. We introduce MP-IB, the first framework to treat…

Machine Learning · Computer Science 2026-05-06 Joydeep Chandra

Modern machine learning models for audio tasks often exhibit superior performance on English and other well-resourced languages, primarily due to the abundance of available training data. This disparity leads to an unfair performance gap…

Computation and Language · Computer Science 2025-11-26 Wesley Bian , Xiaofeng Lin , Guang Cheng

In low-bitrate speech coding, end-to-end speech coding networks aim to learn compact yet expressive features and a powerful decoder in a single network. A challenging problem as such results in unwelcome complexity increase and inferior…

Audio and Speech Processing · Electrical Eng. & Systems 2023-11-16 Haici Yang , Inseon Jang , Minje Kim