English
Related papers

Related papers: Analyzing and Mitigating Inconsistency in Discrete…

200 papers

Audio Descriptions (ADs) convey essential on-screen information, allowing visually impaired audiences to follow videos. To be effective, ADs must form a coherent sequence that helps listeners to visualise the unfolding scene, rather than…

Computer Vision and Pattern Recognition · Computer Science 2025-10-30 Eshika Khandelwal , Junyu Xie , Tengda Han , Max Bain , Arsha Nagrani , Andrew Zisserman , Gül Varol , Makarand Tapaswi

Recent studies on end-to-end (E2E) speech generation with large language models (LLMs) have attracted significant community attention, with multiple works extending text-based LLMs to generate discrete speech tokens. Existing E2E approaches…

Discrete speech representation learning has recently attracted increasing interest in both acoustic and semantic modeling. Existing approaches typically encode 16 kHz waveforms into discrete tokens at a rate of 25 or 50 tokens per second.…

Computation and Language · Computer Science 2025-09-03 Jialong Zuo , Guangyan Zhang , Minghui Fang , Shengpeng Ji , Xiaoqi Jiao , Jingyu Li , Yiwen Guo , Zhou Zhao

Automatic Speech Recognition (ASR) transcripts often contain disfluencies, such as fillers, repetitions, and false starts, which reduce readability and hinder downstream applications like chatbots and voice assistants. If left unaddressed,…

Computation and Language · Computer Science 2026-05-13 Deepak Kumar , Baban Gain , Asif Ekbal

The objective of deep learning methods based on encoder-decoder architectures for music source separation is to approximate either ideal time-frequency masks or spectral representations of the target music source(s). The spectral…

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

We explore the task of improving persona consistency of dialogue agents. Recent models tackling consistency often train with additional Natural Language Inference (NLI) labels or attach trained extra modules to the generative agent for…

Computation and Language · Computer Science 2020-10-07 Hyunwoo Kim , Byeongchang Kim , Gunhee Kim

We propose Universal target audio Separation (UniSep), addressing the separation task on arbitrary mixtures of different types of audio. Distinguished from previous studies, UniSep is performed on unlimited source domains and unlimited…

Automated detection of voice disorders with computational methods is a recent research area in the medical domain since it requires a rigorous endoscopy for the accurate diagnosis. Efficient screening methods are required for the diagnosis…

Quantitative Methods · Quantitative Biology 2018-12-06 Vibhuti Gupta

This paper examines the implications of using the Scale-Invariant Signal-to-Distortion Ratio (SI-SDR) as both evaluation and training objective in supervised speech separation, when the training references contain noise, as is the case with…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-21 Simon Dahl Jepsen , Mads Græsbøll Christensen , Jesper Rindom Jensen

Music generation schemes using language modeling rely on a vocabulary of audio tokens, generally provided as codes in a discrete latent space learnt by an auto-encoder. Multi-stage quantizers are often employed to produce these tokens,…

Sound · Computer Science 2024-06-11 Jean-Marie Lemercier , Simon Rouard , Jade Copet , Yossi Adi , Alexandre Défossez

Machine learning (ML) models memorize and leak training data, causing serious privacy issues to data owners. Training algorithms with differential privacy (DP), such as DP-SGD, have been gaining attention as a solution. However, DP-SGD adds…

Hardware Architecture · Computer Science 2025-10-09 Donghwan Kim , Xin Gu , Jinho Baek , Timothy Lo , Younghoon Min , Kwangsik Shin , Jongryool Kim , Jongse Park , Kiwan Maeng

Audio Language Models (ALM) have emerged as the dominant paradigm for speech and music generation by representing audio as sequences of discrete tokens. Yet, unlike text tokens, which are invertible, audio tokens are extracted from lossy…

Sound · Computer Science 2026-01-14 Simon Rouard , Manu Orsini , Axel Roebel , Neil Zeghidour , Alexandre Défossez

Neural speech models build deeply entangled internal representations, which capture a variety of features (e.g., fundamental frequency, loudness, syntactic category, or semantic content of a word) in a distributed encoding. This complexity…

Computation and Language · Computer Science 2024-10-07 Hosein Mohebbi , Grzegorz Chrupała , Willem Zuidema , Afra Alishahi , Ivan Titov

We propose a dynamic encoder transducer (DET) for on-device speech recognition. One DET model scales to multiple devices with different computation capacities without retraining or finetuning. To trading off accuracy and latency, DET…

Multiple Description Coding (MDC) is a promising error-resilient source coding method that is particularly suitable for dynamic networks with multiple (yet noisy and unreliable) paths. However, conventional MDC video codecs suffer from…

Computer Vision and Pattern Recognition · Computer Science 2024-12-12 Xinyue Hu , Wei Ye , Jiaxiang Tang , Eman Ramadan , Zhi-Li Zhang

Neural text-to-speech (TTS) generally consists of cascaded architecture with separately optimized acoustic model and vocoder, or end-to-end architecture with continuous mel-spectrograms or self-extracted speech frames as the intermediate…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-09 Ruiqing Xue , Yanqing Liu , Lei He , Xu Tan , Linquan Liu , Edward Lin , Sheng Zhao

Audio inpainting seeks to restore missing segments in degraded recordings. Previous diffusion-based methods exhibit impaired performance when the missing region is large. We introduce the first approach that applies discrete diffusion over…

Sound · Computer Science 2026-02-18 Tali Dror , Iftach Shoham , Moshe Buchris , Oren Gal , Haim Permuter , Gilad Katz , Eliya Nachmani

Speaker recognition performance has been greatly improved with the emergence of deep learning. Deep neural networks show the capacity to effectively deal with impacts of noise and reverberation, making them attractive to far-field speaker…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-28 Wenda Chen , Jonathan Huang , Tobias Bocklet

Language models have been effectively applied to modeling natural signals, such as images, video, speech, and audio. A crucial component of these models is the codec tokenizer, which compresses high-dimensional natural signals into…

Audio and Speech Processing · Electrical Eng. & Systems 2025-02-26 Shengpeng Ji , Ziyue Jiang , Wen Wang , Yifu Chen , Minghui Fang , Jialong Zuo , Qian Yang , Xize Cheng , Zehan Wang , Ruiqi Li , Ziang Zhang , Xiaoda Yang , Rongjie Huang , Yidi Jiang , Qian Chen , Siqi Zheng , Zhou Zhao