中文
相关论文

相关论文: Phoneme Discretized Saliency Maps for Explainable …

200 篇论文

Phonemic or phonetic sub-word units are the most commonly used atomic elements to represent speech signals in modern ASRs. However they are not the optimal choice due to several reasons such as: large amount of effort required to handcraft…

计算与语言 · 计算机科学 2016-06-17 Naoya Takahashi , Tofigh Naghibi , Beat Pfister

In automatic speech recognition (ASR), phoneme-based multilingual pre-training and crosslingual fine-tuning is attractive for its high data efficiency and competitive results compared to subword-based models. However, Weighted Finite State…

声音 · 计算机科学 2025-06-06 Te Ma , Min Bi , Saierdaer Yusuyin , Hao Huang , Zhijian Ou

Deepfake speech utterances can be forged by replacing one or more words in a bona fide utterance with semantically different words synthesized with speech-generative models. While a dedicated synthetic word detector could be developed, we…

音频与语音处理 · 电气工程与系统科学 2026-03-03 Hoan My Tran , Xin Wang , Wanying Ge , Xuechen Liu , Junichi Yamagishi

With the rise of Speech Large Language Models (SpeechLLMs), two dominant approaches have emerged for speech processing: discrete tokens and continuous features. Each approach has demonstrated strong capabilities in audio-related processing…

计算与语言 · 计算机科学 2025-08-26 Dingdong Wang , Junan Li , Mingyu Cui , Dongchao Yang , Xueyuan Chen , Helen Meng

Nearly all existing visual saliency models by far have focused on predicting a universal saliency map across all observers. Yet psychology studies suggest that visual attention of different observers can vary significantly under specific…

计算机视觉与模式识别 · 计算机科学 2018-06-19 Yanyu Xu , Shenghua Gao , Junru Wu , Nianyi Li , Jingyi Yu

Speech fluency/disfluency can be evaluated by analyzing a range of phonetic and prosodic features. Deep neural networks are commonly trained to map fluency-related features into the human scores. However, the effectiveness of deep…

计算与语言 · 计算机科学 2023-05-22 Kaiqi Fu , Shaojun Gao , Shuju Shi , Xiaohai Tian , Wei Li , Zejun Ma

In recent years, a number of time-domain speech separation methods have been proposed. However, most of them are very sensitive to the environments and wide domain coverage tasks. In this paper, from the time-frequency domain perspective,…

音频与语音处理 · 电气工程与系统科学 2022-02-01 Jiangyu Han , Yanhua Long , Lukas Burget , Jan Cernocky

The rapid advancement of generative AI has made audio deepfakes increasingly indistinguishable from authentic human vocals, posing significant threats to persons-of-interest (POI) such as public figures. Current detection systems primarily…

声音 · 计算机科学 2026-05-19 Jun Xue , Tong Zhang , Zhuolin Yi , Yihuan Huang , Yi Chai , Yiyang Zhang , Yanzhen Ren

In this work, we address the challenge of generalizable audio deepfake detection (ADD) across diverse speech synthesis paradigms-including conventional text-to-speech (TTS) systems and modern diffusion or flow-matching (FM) based…

音频与语音处理 · 电气工程与系统科学 2025-11-17 Farhan Sheth , Girish , Mohd Mujtaba Akhtar , Muskaan Singh

Recent advances in generative AI have made the creation of speech deepfakes widely accessible, posing serious challenges to digital trust. To counter this, various speech deepfake detection strategies have been proposed, including…

声音 · 计算机科学 2025-07-14 Davide Salvi , Viola Negroni , Sara Mandelli , Paolo Bestagini , Stefano Tubaro

We investigate the efficiency of two very different spoken term detection approaches for transcription when the available data is insufficient to train a robust ASR system. This work is grounded in very low-resource language documentation…

计算与语言 · 计算机科学 2021-06-14 Éric Le Ferrand , Steven Bird , Laurent Besacier

The paper describes a novel approach to Spoken Term Detection (STD) in large spoken archives using deep LSTM networks. The work is based on the previous approach of using Siamese neural networks for STD and naturally extends it to directly…

计算与语言 · 计算机科学 2022-10-24 Jan Švec , Luboš Šmídl , Josef V. Psutka , Aleš Pražák

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…

声音 · 计算机科学 2025-07-18 Luca Della Libera , Cem Subakan , Mirco Ravanelli

Discrete audio tokens are compact representations that aim to preserve perceptual quality, phonetic content, and speaker characteristics while enabling efficient storage and inference, as well as competitive performance across diverse…

In this paper, a novel approach is proposed for the recognition of Persian phonemes in the Persian Consonant-Vowel Combination (PCVC) speech dataset. Nowadays, deep neural networks play a crucial role in classification tasks. However, the…

音频与语音处理 · 电气工程与系统科学 2020-03-24 Saber Malekzadeh , Mohammad Hossein Gholizadeh , Hossein Ghayoumi zadeh , Seyed Naser Razavi

The rise of AI-driven generative models has enabled the creation of highly realistic speech deepfakes - synthetic audio signals that can imitate target speakers' voices - raising critical security concerns. Existing methods for detecting…

声音 · 计算机科学 2025-03-25 Emma Coletta , Davide Salvi , Viola Negroni , Daniele Ugo Leonzio , Paolo Bestagini

This work profoundly analyzes discrete self-supervised speech representations (units) through the eyes of Generative Spoken Language Modeling (GSLM). Following the findings of such an analysis, we propose practical improvements to the…

计算与语言 · 计算机科学 2023-06-09 Amitay Sicherman , Yossi Adi

Discrete representation has shown advantages in speech generation tasks, wherein discrete tokens are derived by discretizing hidden features from self-supervised learning (SSL) pre-trained models. However, the direct application of speech…

声音 · 计算机科学 2024-06-21 Yuxun Tang , Yuning Wu , Jiatong Shi , Qin Jin

Speech contains information that is clinically relevant to some diseases, which has the potential to be used for health assessment. Recent work shows an interest in applying deep learning algorithms, especially pretrained large speech…

声音 · 计算机科学 2024-07-02 Hok-Shing Lau , Mark Huntly , Nathon Morgan , Adesua Iyenoma , Biao Zeng , Tim Bashford

Diffusion models form an important class of generative models today, accounting for much of the state of the art in cutting edge AI research. While numerous extensions beyond image and video generation exist, few of such approaches address…

机器学习 · 计算机科学 2025-04-30 Hao Luan , See-Kiong Ng , Chun Kai Ling