English
Related papers

Related papers: Beyond Fixed Frames: Dynamic Character-Aligned Spe…

200 papers

Diffusion speech enhancement on discrete audio codec features gain immense attention due to their improved speech component reconstruction capability. However, they usually suffer from high inference computational complexity due to multiple…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-30 Yihui Fu , Tim Fingscheidt

Dysarthric speech recognition often suffers from performance degradation due to the intrinsic diversity of dysarthric severity and extrinsic disparity from normal speech. To bridge these gaps, we propose a Dynamic Phoneme-level Contrastive…

Computation and Language · Computer Science 2025-02-04 Wonjun Lee , Solee Im , Heejin Do , Yunsu Kim , Jungseul Ok , Gary Geunbae Lee

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…

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

Contextual biasing (CB) improves automatic speech recognition for rare and unseen phrases. Recent studies have introduced dynamic vocabulary, which represents context phrases as expandable tokens in autoregressive (AR) models. This method…

Computation and Language · Computer Science 2025-06-04 Yui Sudo , Yosuke Fukumoto , Muhammad Shakeel , Yifan Peng , Chyi-Jiunn Lin , Shinji Watanabe

Large Audio Language Models (LALMs) demonstrate impressive performance across diverse tasks, ranging from speech recognition to general audio understanding. However, their scalability is limited by the quadratic complexity of attention and…

Audio and Speech Processing · Electrical Eng. & Systems 2025-11-27 Saurabhchand Bhati , Samuel Thomas , Hilde Kuehne , Rogerio Feris , James Glass

While existing speech audio codecs designed for compression exploit limited forms of temporal redundancy and allow for multi-scale representations, they tend to represent all features of audio in the same way. In contrast, generative voice…

Sound · Computer Science 2025-09-22 Ryan Collette , Ross Greenwood , Serena Nicoll

State-of-the-art sequence-to-sequence acoustic networks, that convert a phonetic sequence to a sequence of spectral features with no explicit prosody prediction, generate speech with close to natural quality, when cascaded with neural…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-26 Slava Shechtman , Carmel Rabinovitz , Alex Sorin , Zvi Kons , Ron Hoory

Convolutional layers with 1-D filters are often used as frontend to encode audio signals. Unlike fixed time-frequency representations, they can adapt to the local characteristics of input data. However, 1-D filters on raw audio are hard to…

Sound · Computer Science 2024-09-02 Daniel Haider , Felix Perfler , Vincent Lostanlen , Martin Ehler , Peter Balazs

Transformers are designed for discrete tokens, yet many real-world signals are continuous processes observed through noisy sampling. Discrete tokenizations (raw values, patches, finite differences) can be brittle in low signal-to-noise…

Machine Learning · Computer Science 2026-01-21 Griffin Kearney

Recent advances in Video Large Language Models (VLLMs) have achieved remarkable video understanding capabilities, yet face critical efficiency bottlenecks due to quadratic computational growth with lengthy visual token sequences of long…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Yulin Li , Haokun Gui , Ziyang Fan , Junjie Wang , Bin Kang , Bin Chen , Zhuotao Tian

Tokenising continuous speech into sequences of discrete tokens and modelling them with language models (LMs) has led to significant success in text-to-speech (TTS) synthesis. Although these models can generate speech with high quality and…

Sound · Computer Science 2024-08-30 Zehai Tu , Guangyan Zhang , Yiting Lu , Adaeze Adigwe , Simon King , Yiwen Guo

In speech processing pipelines, improving the quality and intelligibility of real-world recordings is crucial. While supervised regression is the primary method for speech enhancement, audio tokenization is emerging as a promising…

Sound · Computer Science 2025-07-18 Luca Della Libera , Cem Subakan , Mirco Ravanelli

The neural codec language model (CLM) has demonstrated remarkable performance in text-to-speech (TTS) synthesis. However, troubled by ``recency bias", CLM lacks sufficient attention to coarse-grained information at a higher temporal scale,…

Sound · Computer Science 2024-09-19 Haohan Guo , Fenglong Xie , Dongchao Yang , Xixin Wu , Helen Meng

Inspired by the success of deep neural networks (DNNs) in speech processing, this paper presents Deep Vocoder, a direct end-to-end low bit rate speech compression method with deep autoencoder (DAE). In Deep Vocoder, DAE is used for…

Multimedia · Computer Science 2019-05-15 Gang Min , Changqing Zhang , Xiongwei Zhang , Wei Tan

Existing text-to-speech systems predominantly focus on single-sentence synthesis and lack adequate contextual modeling as well as fine-grained performance control capabilities for generating coherent multicast audiobooks. To address these…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-23 Min Liu , JingJing Yin , Xiang Zhang , Siyu Hao , Yanni Hu , Bin Lin , Yuan Feng , Hongbin Zhou , Jianhao Ye

Neural audio codecs have recently gained popularity because they can represent audio signals with high fidelity at very low bitrates, making it feasible to use language modeling approaches for audio generation and understanding. Residual…

Sound · Computer Science 2024-10-21 Hubert Siuzdak , Florian Grötschla , Luca A. Lanzendörfer

This paper introduces DashengTokenizer, a continuous audio tokenizer engineered for joint use in both understanding and generation tasks. Unlike conventional approaches, which train acoustic tokenizers and subsequently integrate frozen…

In speech enhancement, an end-to-end deep neural network converts a noisy speech signal to a clean speech directly in time domain without time-frequency transformation or mask estimation. However, aggregating contextual information from a…

Sound · Computer Science 2020-02-10 Kai Zhen , Mi Suk Lee , Minje Kim

We propose using self-supervised discrete representations for the task of speech resynthesis. To generate disentangled representation, we separately extract low-bitrate representations for speech content, prosodic information, and speaker…