Skip to Content

207 Results Found

  • Article
  • Open Access
5 Citations
3,645 Views
21 Pages

3D Dynamic Spatiotemporal Atlas of the Vocal Tract during Consonant–Vowel Production from 2D Real Time MRI

  • Ioannis K. Douros,
  • Yu Xie,
  • Chrysanthi Dourou,
  • Karyna Isaieva and ,
  • Pierre-André Vuissoz,
  • Jacques Felblinger and
  • Yves Laprie
  • + 2 authors+ 0 author

25 August 2022

In this work, we address the problem of creating a 3D dynamic atlas of the vocal tract that captures the dynamics of the articulators in all three dimensions in order to create a global speaker model independent of speaker-specific characteristics. T...

(This article belongs to the Section Medical Imaging)
  • Article
  • Open Access
2 Citations
5,836 Views
20 Pages

16 March 2025

Voice activity detection (VAD) is the process of automatically determining whether a person is speaking and identifying the timing of their speech in an audiovisual data. Traditionally, this task has been tackled by processing either audio signals or...

(This article belongs to the Section Information Applications)
  • Article
  • Open Access
1,332 Views
24 Pages

Speaker anonymization effectively conceals speaker identity in speech signals to protect privacy. To address issues in existing anonymization systems, including reduced voice distinguishability, limited anonymized voices, reliance on an external spea...

(This article belongs to the Topic Generative AI and Interdisciplinary Applications)
  • Article
  • Open Access
14 Citations
15,773 Views
16 Pages

Voice cloning aims to synthesize the voice with a new speaker’s timbre from a small amount of the new speaker’s speech. Current voice cloning methods, which focus on modeling speaker timbre, can synthesize speech with similar speaker timb...

(This article belongs to the Section Artificial Intelligence)
  • Article
  • Open Access
8 Citations
5,934 Views
12 Pages

CycleDiffusion: Voice Conversion Using Cycle-Consistent Diffusion Models

  • Dongsuk Yook,
  • Geonhee Han,
  • Hyung-Pil Chang and
  • In-Chul Yoo

21 October 2024

Voice conversion (VC) refers to the technique of modifying one speaker’s voice to mimic another’s while retaining the original linguistic content. This technology finds its applications in fields such as speech synthesis, accent modificat...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
210 Views
18 Pages

Multi-Task Flow Matching Speech Enhancement Method with Dual Guidance of Semantic Understanding and Speaker Perception

  • Bingyu Dai,
  • Xia Zou,
  • Yihao Li,
  • Chong Jia and ,
  • Meng Sun,
  • Yongqiang Xie and
  • Xiongwei Zhang
  • + 2 authors+ 0 author

9 October 2026

Generative speech enhancement models often suffer from the “generative hallucination” issue, where artifacts are introduced or original speech characteristics are distorted during reconstruction due to insufficient prior constraints, seve...

(This article belongs to the Special Issue Feature Papers in Circuit and Signal Processing, 2nd Edition)
  • Article
  • Open Access
11 Citations
5,351 Views
12 Pages

3 December 2023

Speech synthesis is a technology that converts text into speech waveforms. With the development of deep learning, neural network-based speech synthesis technology is being researched in various fields, and the quality of synthesized speech has signif...

(This article belongs to the Section Intelligent Sensors)
  • Article
  • Open Access
9 Citations
4,643 Views
17 Pages

9 July 2019

Restricted Boltzmann Machines (RBMs) have shown success in both the front-end and backend of speaker verification systems. In this paper, we propose applying RBMs to the front-end for the tasks of speaker clustering and speaker tracking in TV broadca...

(This article belongs to the Special Issue IberSPEECH 2018: Speech and Language Technologies for Iberian Languages)
  • Article
  • Open Access
11 Citations
6,141 Views
16 Pages

22 December 2022

Emotion recognition in conversation (ERC) is receiving more and more attention, as interactions between humans and machines increase in a variety of services such as chat-bot and virtual assistants. As emotional expressions within a conversation can...

(This article belongs to the Special Issue Machine Learning in Pattern Recognition)
  • Article
  • Open Access
4 Citations
5,601 Views
22 Pages

The lenition of Spanish intervocalic voiced stops, commonly grouped as /bdg/, has increasingly been examined within Spanish as a Heritage Language research. This study seeks to identify social, phonetic, and lexical factors that predict the degree of...

(This article belongs to the Special Issue Contemporary Advances in Linguistic Research on Heritage Spanish)
  • Article
  • Open Access
12 Citations
6,579 Views
13 Pages

21 November 2018

Common sound source localization algorithms focus on localizing all the active sources in the environment. While the source identities are generally unknown, retrieving the location of a speaker of interest requires extra effort. This paper addresses...

(This article belongs to the Section Acoustics and Vibrations)
  • Article
  • Open Access
7 Citations
4,937 Views
19 Pages

U-Vectors: Generating Clusterable Speaker Embedding from Unlabeled Data

  • Muhammad Firoz Mridha,
  • Abu Quwsar Ohi,
  • Muhammad Mostafa Monowar,
  • Md. Abdul Hamid and ,
  • Md. Rashedul Islam and
  • Yutaka Watanobe
  • + 1 author+ 0 author

27 October 2021

Speaker recognition deals with recognizing speakers by their speech. Most speaker recognition systems are built upon two stages, the first stage extracts low dimensional correlation embeddings from speech, and the second performs the classification t...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
7 Citations
2,812 Views
19 Pages

12 February 2023

Endangered language generally has low-resource characteristics, as an immaterial cultural resource that cannot be renewed. Automatic speech recognition (ASR) is an effective means to protect this language. However, for low-resource language, native s...

(This article belongs to the Special Issue Advances in Acoustic Sensors and Deep Audio Pattern Recognition)
  • Article
  • Open Access
2 Citations
2,808 Views
20 Pages

LJ-TTS: A Paired Real and Synthetic Speech Dataset for Single-Speaker TTS Analysis

  • Viola Negroni,
  • Davide Salvi,
  • Luca Comanducci,
  • Taiba Majid Wani and ,
  • Madleen Uecker,
  • Irene Amerini,
  • Stefano Tubaro and
  • Paolo Bestagini
  • + 3 authors+ 0 author

30 December 2025

In this paper, we present LJ-TTS, a large-scale single-speaker dataset of real and synthetic speech designed to support research in text-to-speech (TTS) synthesis and analysis. The dataset builds upon high-quality recordings of a single English speak...

(This article belongs to the Special Issue Emerging Trends in Generative-AI Based Audio Processing)
  • Article
  • Open Access
3 Citations
6,918 Views
19 Pages

Apocope in Heritage Italian

  • Anissa Baird,
  • Angela Cristiano and
  • Naomi Nagy

Apocope (deletion of word-final vowels) and word-final vowel reduction are hallmarks of southern Italian varieties. To investigate whether heritage speakers reproduce the complex variable patterns of these processes, we analyze spontaneous speech of...

(This article belongs to the Special Issue Social and Psychological Factors in Bilingual Speech Production)
  • Article
  • Open Access
13 Citations
4,325 Views
16 Pages

13 August 2022

Silent speech interfaces (SSIs) convert non-audio bio-signals, such as articulatory movement, to speech. This technology has the potential to recover the speech ability of individuals who have lost their voice but can still articulate (e.g., laryngec...

(This article belongs to the Special Issue Future Speech Interfaces with Sensors and Machine Intelligence)
  • Article
  • Open Access
4 Citations
3,903 Views
21 Pages

Arabic Emotional Voice Conversion Using English Pre-Trained StarGANv2-VC-Based Model

  • Ali H. Meftah,
  • Yousef A. Alotaibi and
  • Sid-Ahmed Selouani

28 November 2022

The goal of emotional voice conversion (EVC) is to convert the emotion of a speaker’s voice from one state to another while maintaining the original speaker’s identity and the linguistic substance of the message. Research on EVC in the Ar...

(This article belongs to the Special Issue Audio, Speech and Language Processing)
  • Article
  • Open Access
3,564 Views
20 Pages

Use of Embedded Clauses in Heritage and Monolingual Russian

  • Maria Martynova,
  • Yulia Zuban,
  • Natalia Gagarina and
  • Luka Szucsich

This study investigates the production of clausal embeddings by 195 Russian speakers (67 monolingually raised speakers, 68 heritage speakers in the US, and 60 heritage speakers in Germany) in different communicative situations varying by formality (f...

(This article belongs to the Special Issue Heritage Russian Bilingualism across the Lifespan)
  • Article
  • Open Access
6 Citations
3,626 Views
16 Pages

16 March 2021

This paper addresses an automatic proficiency evaluation and speech recognition for second language (L2) speech. The proposed method recognizes the speech uttered by the L2 speaker, measures a variety of fluency scores, and evaluates the proficiency...

(This article belongs to the Special Issue Artificial Intelligence for Multimedia Signal Processing)
  • Article
  • Open Access
1 Citations
2,412 Views
16 Pages

Effects of Sinusoidal Model on Non-Parallel Voice Conversion with Adversarial Learning

  • Mohammed Salah Al-Radhi,
  • Tamás Gábor Csapó and
  • Géza Németh

15 August 2021

Voice conversion (VC) transforms the speaking style of a source speaker to the speaking style of a target speaker by keeping linguistic information unchanged. Traditional VC techniques rely on parallel recordings of multiple speakers uttering the sam...

  • Article
  • Open Access
243 Views
21 Pages

27 October 2026

This study investigates contact-induced changes in the language of Tagalog–Italian bilingual heritage speakers in Italy, focusing on word order and voice. Drawing on data from 85 participants across four groups—Tagalog homeland speakers,...

(This article belongs to the Special Issue Heritage Languages in Italy: New Issues and Perspectives)
  • Article
  • Open Access
1 Citations
6,248 Views
27 Pages

14 May 2025

Voice conversion (VC) is an advanced technology that enables the transformation of raw speech into high-quality audio resembling the target speaker’s voice while preserving the original linguistic content and prosodic patterns. In this study, w...

(This article belongs to the Special Issue Deep Learning for Speech, Image and Language Processing)
  • Article
  • Open Access
3 Citations
2,609 Views
13 Pages

Speaker Recognition Based on the Joint Loss Function

  • Tengteng Feng,
  • Houbin Fan,
  • Fengpei Ge,
  • Shuxin Cao and
  • Chunyan Liang

15 August 2023

The statistical pyramid dense time-delay neural network (SPD-TDNN) model makes it difficult to deal with the imbalance of training data, poses a high risk of overfitting, and has weak generalization ability. To solve these problems, we propose a meth...

(This article belongs to the Special Issue Machine Learning in Music/Audio Signal Processing)
  • Article
  • Open Access
8 Citations
3,881 Views
11 Pages

22 December 2021

The majority of recent speaker verification tasks are studied under open-set evaluation scenarios considering real-world conditions. The characteristics of these tasks imply that the generalization towards unseen speakers is a critical capability. Th...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
4 Citations
2,740 Views
14 Pages

Multisensory Fusion for Unsupervised Spatiotemporal Speaker Diarization

  • Paris Xylogiannis,
  • Nikolaos Vryzas,
  • Lazaros Vrysis and
  • Charalampos Dimoulas

29 June 2024

Speaker diarization consists of answering the question of “who spoke when” in audio recordings. In meeting scenarios, the task of labeling audio with the corresponding speaker identities can be further assisted by the exploitation of spat...

(This article belongs to the Special Issue Multimodal Sensing Technologies for IoT and AI-Enabled Systems)
  • Article
  • Open Access
20 Citations
10,607 Views
14 Pages

25 November 2019

Speaker diarization systems aim to find ‘who spoke when?’ in multi-speaker recordings. The dataset usually consists of meetings, TV/talk shows, telephone and multi-party interaction recordings. In this paper, we propose a novel multimodal...

(This article belongs to the Special Issue Speech, Acoustics, Audio Signal Processing and Applications in Sensors)
  • Article
  • Open Access
2 Citations
1,811 Views
20 Pages

Machine Unlearning for Speaker-Agnostic Detection of Gender-Based Violence Condition in Speech

  • Emma Reyner-Fuentes,
  • Esther Rituerto-González and
  • Carmen Peláez-Moreno

19 November 2025

Gender-based violence is a pervasive social and public health issue that severely impacts women’s mental health, often leading to conditions such as anxiety, depression, post-traumatic stress disorder, and substance abuse. Identifying the combi...

(This article belongs to the Section Applied Biosciences and Bioengineering)
  • Article
  • Open Access
10 Citations
4,916 Views
25 Pages

1 December 2022

This article presents the Automatic Speaker Recognition System (ASR System), which successfully resolves problems such as identification within an open set of speakers and the verification of speakers in difficult recording conditions similar to tele...

(This article belongs to the Special Issue Biometrics Recognition Systems)
  • Article
  • Open Access
15 Citations
6,904 Views
17 Pages

26 October 2020

Speaker identification is gaining popularity, with notable applications in security, automation, and authentication. For speaker identification, deep-convolutional-network-based approaches, such as SincNet, are used as an alternative to i-vectors. Co...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
1 Citations
2,573 Views
14 Pages

2 October 2023

At present, a prevalent approach to speaker diarization is clustering based on speaker embeddings. However, this method encounters two primary issues. Firstly, it cannot directly minimize the diarization error during the training process; secondly, t...

  • Article
  • Open Access
7 Citations
3,308 Views
14 Pages

2 November 2023

We present an any-to-one voice conversion (VC) system, using an autoregressive model and LPCNet vocoder, aimed at enhancing the converted speech in terms of naturalness, intelligibility, and speaker similarity. As the name implies, non-parallel any-t...

(This article belongs to the Section Acoustics and Vibrations)
  • Article
  • Open Access
7 Citations
3,656 Views
12 Pages

Addressing Text-Dependent Speaker Verification Using Singing Speech

  • Yan Shi,
  • Juanjuan Zhou,
  • Yanhua Long,
  • Yijie Li and
  • Hongwei Mao

28 June 2019

The automatic speaker verification (ASV) has achieved significant progress in recent years. However, it is still very challenging to generalize the ASV technologies to new, unknown and spoofing conditions. Most previous studies focused on extracting...

(This article belongs to the Section Acoustics and Vibrations)
  • Article
  • Open Access
310 Views
20 Pages

19 September 2026

This paper proposes a novel hybrid voice conversion framework, termed VQ-CycleDiffusion, which integrates vector quantization (VQ) with CycleDiffusion to address the inherent limitations of continuous latent representations in diffusion-based models....

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
331 Views
21 Pages

2 September 2026

Speaker recognition models are typically enrolled using neutral speech, yet real users rarely speak under emotionally neutral conditions. Emotion alters prosody, spectral structure, articulation, and speaking rate, shifting utterances away from the a...

(This article belongs to the Special Issue Signal Processing and Machine Learning, 2nd Edition)
  • Article
  • Open Access
1 Citations
3,074 Views
21 Pages

10 March 2025

This study addresses the challenges of complex noise and short speech in civil aviation air-ground communication scenarios and proposes a novel speaker identification model, Chrono-ECAPA-TDNN (CET). The aim of the study is to enhance the accuracy and...

  • Review
  • Open Access
11 Citations
13,402 Views
19 Pages

14 February 2025

Recorded audio often contains speech from multiple people in conversation. It is useful to label such signals with speaker turns, noting when each speaker is talking and identifying each speaker. This paper discusses how to process speech signals to...

(This article belongs to the Section Electrical, Electronics and Communications Engineering)
  • Article
  • Open Access
6 Citations
5,040 Views
30 Pages

17 January 2024

In environments characterised by noise or the absence of audio signals, visual cues, notably facial and lip movements, serve as valuable substitutes for missing or corrupted speech signals. In these scenarios, speech reconstruction can potentially ge...

(This article belongs to the Special Issue Advanced Technology in Speech and Acoustic Signal Processing)
  • Article
  • Open Access
829 Views
23 Pages

This paper investigates variation on the level of lexis in Austrian German across registers with an apparent-time approach, drawing on data from a large-scale online survey of lexical variation conducted across Austria between 2021 and 2023, comprisi...

(This article belongs to the Special Issue Advances in Variationist Linguistics on German—Focus on Lexis and Pragmatics)
  • Article
  • Open Access
6 Citations
4,828 Views
15 Pages

GERP: A Personality-Based Emotional Response Generation Model

  • Ziyi Zhou,
  • Ying Shen,
  • Xuri Chen and
  • Dongqing Wang

19 April 2023

It is important for chatbots to emotionally communicate with users. However, most emotional response generation models generate responses simply based on a specified emotion, neglecting the impacts of speaker’s personality on emotional expressi...

(This article belongs to the Special Issue Advances in Speech and Language Processing)
  • Article
  • Open Access
4 Citations
4,001 Views
14 Pages

Self Attention Networks in Speaker Recognition

  • Pooyan Safari,
  • Miquel India and
  • Javier Hernando

24 May 2023

Recently, there has been a significant surge of interest in Self-Attention Networks (SANs) based on the Transformer architecture. This can be attributed to their notable ability for parallelization and their impressive performance across various Natu...

  • Article
  • Open Access
3 Citations
3,799 Views
18 Pages

14 October 2022

This study investigates the L1 influence on the use of accentual patterns, choice of prenuclear pitch accent types and their realization on L2 prosody. We use Mennen’s LILt model as a framework for our analysis. We recorded ten Bulgarian female...

(This article belongs to the Special Issue The Effects of Cross-Language Differences on Bilingual Production and/or Perception of Sentence-Level Intonation)
  • Article
  • Open Access
2 Citations
1,977 Views
18 Pages

28 August 2024

Misunderstandings in dyadic interactions often persist despite our best efforts, particularly between native and non-native speakers, resembling a broken duet that refuses to harmonise. This paper delves into the computational mechanisms underpinning...

(This article belongs to the Special Issue From Functional Imaging to Free Energy—Dedicated to Professor Karl Friston on the Occasion of His 65th Birthday)
  • Article
  • Open Access
4 Citations
3,228 Views
14 Pages

17 October 2020

One of the most important parts of a text-independent speaker verification system is speaker embedding generation. Previous studies demonstrated that shortcut connections-based multi-layer aggregation improves the representational power of a speaker...

(This article belongs to the Special Issue Human Computer Interaction for Intelligent Systems)
  • Article
  • Open Access
16 Citations
6,046 Views
13 Pages

27 February 2023

Lip reading technology refers to the analysis of the visual information of the speaker’s mouth movements to recognize the content of the speaker’s speech. As one of the important aspects of human–computer interaction, the technology...

  • Article
  • Open Access
3 Citations
2,633 Views
15 Pages

Frame-Based Phone Classification Using EMG Signals

  • Inge Salomons,
  • Eder del Blanco,
  • Eva Navas,
  • Inma Hernáez and
  • Xabier de Zuazo

30 June 2023

This paper evaluates the impact of inter-speaker and inter-session variability on the development of a silent speech interface (SSI) based on electromyographic (EMG) signals from the facial muscles. The final goal of the SSI is to provide a communica...

(This article belongs to the Special Issue IberSPEECH 2022: Speech and Language Technologies for Iberian Languages)
  • Article
  • Open Access
1 Citations
4,490 Views
14 Pages

Speaker Verification Based on Channel Attention and Adaptive Joint Loss

  • Houbin Fan,
  • Jun Li,
  • Fengpei Ge and
  • Chunyan Liang

In deep learning-based speaker verification, the loss function plays a crucial role. Most systems rely on a single loss function, or simply sum multiple losses with manually adjusted weights, increasing experimental complexity and failing to fully le...

  • Article
  • Open Access
6 Citations
2,986 Views
21 Pages

BIM-Based Adversarial Attacks Against Speech Deepfake Detectors

  • Wendy Edda Wang,
  • Davide Salvi,
  • Viola Negroni,
  • Daniele Ugo Leonzio and ,
  • Paolo Bestagini and
  • Stefano Tubaro
  • + 1 author+ 0 author

Automatic Speaker Verification (ASV) systems are increasingly employed to secure access to services and facilities. However, recent advances in speech deepfake generation pose serious threats to their reliability. Modern speech synthesis models can c...

(This article belongs to the Section Computer Science & Engineering)
  • Article
  • Open Access
9 Citations
5,102 Views
16 Pages

Strong Generalized Speech Emotion Recognition Based on Effective Data Augmentation

  • Huawei Tao,
  • Shuai Shan,
  • Ziyi Hu,
  • Chunhua Zhu and
  • Hongyi Ge

30 December 2022

The absence of labeled samples limits the development of speech emotion recognition (SER). Data augmentation is an effective way to address sample sparsity. However, there is a lack of research on data augmentation algorithms in the field of SER. In...

(This article belongs to the Special Issue Machine and Deep Learning for Affective Computing)
  • Article
  • Open Access
570 Views
17 Pages

11 September 2026

Singlish is a code-mixed creole formed from English and multiple Asian languages and dialects, predominantly spoken in Singapore. Translation of Singlish to standard UK English broadens comprehension of the creole and supports downstream analyses suc...

(This article belongs to the Special Issue Natural Language Processing in the Era of Big Data)
  • Article
  • Open Access
12 Citations
14,099 Views
26 Pages

6 December 2021

Heritage language variation and change provides an opportunity to examine the interplay of contact-induced and language-internal effects while extending the variationist framework beyond monolingual speakers and majority languages. Using data from th...

(This article belongs to the Special Issue Heritage Speaker Phonetics and Phonology: Testing Models and Expanding the Range of Data)

of 5