Výsledky vyhľadávania - "Electrical Engineering and Systems Science - Audio and Speech Processing"

Generalized Domain Adaptation Framework for Parametric Back-End in Speaker Recognition Autor Qiongqiong Wang, Koji Okabe, Kong Aik Lee, Takafumi Koshinaka

Získať plný text

Versatile Time-Frequency Representations Realized by Convex Penalty on Magnitude Spectrogram Autor Keidai Arai, Koki Yamada, Kohei Yatabe

Získať plný text

Investigation of Japanese PnG BERT Language Model in Text-to-Speech Synthesis for Pitch Accent Language Autor Yusuke Yasuda, Tomoki Toda

Získať plný text

Expression-Preserving Face Frontalization Improves Visually Assisted Speech Processing Autor Zhiqi Kang, Mostafa Sadeghi, Radu Horaud, Xavier Alameda-Pineda

Získať plný text

CASA-based speaker identification using cascaded GMM-CNN classifier in noisy and emotional talking conditions Autor Nawel Nemmour, Keikichi Hirose, Shibani Hamsa, Ismail Shahin, Ali Bou Nassif

Získať plný text

Bass Accompaniment Generation Via Latent Diffusion Autor Pasini, Marco, Grachten, Maarten, Lattner, Stefan

“…The ability to automatically generate music that appropriately matches an arbitrary input track is a challenging task. We present a novel controllable system…”
Získať plný text

GEDI: Gammachirp envelope distortion index for predicting intelligibility of enhanced speech Autor Shoko Araki, Keisuke Kinoshita, Katsuhiko Yamamoto, Toshio Irino, Tomohiro Nakatani

Získať plný text

Learning and controlling the source-filter representation of speech with a variational autoencoder Autor Sadok, Samir, Leglaive, Simon, Girin, Laurent, Alameda-Pineda, Xavier, Seguier, Renaud

Získať plný text

RISC: A Corpus for Shout Type Classification and Shout Intensity Prediction Autor Takahiro Fukumori, Taito Ishida, Yoichi Yamashita

Získať plný text

PeriodGrad: Towards Pitch-Controllable Neural Vocoder Based on a Diffusion Probabilistic Model Autor Hono, Yukiya, Hashimoto, Kei, Nankaku, Yoshihiko, Tokuda, Keiichi

“…This paper presents a neural vocoder based on a denoising diffusion probabilistic model (DDPM) incorporating explicit periodic signals as auxiliary…”
Získať plný text

MOS-FAD: Improving Fake Audio Detection Via Automatic Mean Opinion Score Prediction Autor Zhou, Wangjin, Yang, Zhengdong, Chu, Chenhui, Li, Sheng, Dabre, Raj, Zhao, Yi, Tatsuya, Kawahara

“…IEEE Automatic Mean Opinion Score (MOS) prediction is employed to evaluate the quality of synthetic speech. This study extends the application of predicted MOS…”
Získať plný text

FastMVAE2: On Improving and Accelerating the Fast Variational Autoencoder-Based Source Separation Algorithm for Determined Mixtures Autor Li Li, Hirokazu Kameoka, Shoji Makino

Získať plný text

Data Driven Grapheme-to-Phoneme Representations for a Lexicon-Free Text-to-Speech Autor Garg, Abhinav, Kim, Jiyeon, Khyalia, Sushil, Kim, Chanwoo, Gowda, Dhananjaya

“…Grapheme-to-Phoneme (G2P) is an essential first step in any modern, high-quality Text-to-Speech (TTS) system. Most of the current G2P systems rely on carefully…”
Získať plný text

ELP-Adapters: Parameter Efficient Adapter Tuning for Various Speech Processing Tasks Autor Nakamasa Inoue, Shinta Otake, Takumi Hirose, Masanari Ohi, Rei Kawakami

Získať plný text

The VoicePrivacy 2022 Challenge: Progress and Perspectives in Voice Anonymisation Autor Michele Panariello, Natalia Tomashenko, Xin Wang, Xiaoxiao Miao, Pierre Champion, Hubert Nourtel, Massimiliano Todisco, Nicholas Evans, Emmanuel Vincent, Junichi Yamagishi

Získať plný text

A Large-Scale Evaluation of Speech Foundation Models Autor Shu-wen Yang, Heng-Jui Chang, Zili Huang, Andy T. Liu, Cheng-I Lai, Haibin Wu, Jiatong Shi, Xuankai Chang, Hsiang-Sheng Tsai, Wen-Chin Huang, Tzu-hsun Feng, Po-Han Chi, Yist Y. Lin, Yung-Sung Chuang, Tzu-Hsien Huang, Wei-Cheng Tseng, Kushal Lakhotia, Shang-Wen Li, Abdelrahman Mohamed, Shinji Watanabe, Hung-yi Lee

Získať plný text

Localizing Acoustic Energy in Sound Field Synthesis by Directionally Weighted Exterior Radiation Suppression Autor Tomita, Yoshihide, Koyama, Shoichi, Saruwatari, Hiroshi

“…A method for synthesizing the desired sound field while suppressing the exterior radiation power with directional weighting is proposed. The exterior radiation…”
Získať plný text

Optimizing multi-user indoor sound communications with acoustic reconfigurable metasurfaces Autor Hongkuan Zhang, Qiyuan Wang, Mathias Fink, Guancong Ma

Získať plný text

A Novel Temporal Attentive-Pooling based Convolutional Recurrent Architecture for Acoustic Signal Enhancement Autor Tassadaq Hussain, Wei-Chien Wang, Mandar Gogate, Kia Dashtipour, Yu Tsao, Xugang Lu, Adeel Ahsan, Amir Hussain

Získať plný text

Decoupling Speaker-Independent Emotions for Voice Conversion via Source-Filter Networks Autor Zhaojie Luo, Shoufeng Lin, Rui Liu, Jun Baba, Yuichiro Yoshikawa, Hiroshi Ishiguro

Získať plný text