Suchergebnisse - Electrical Engineering and Systems Science - Audio and Speech Processing

Procurement Of Dsp Enabled Evaluation Kit For Speech And Audio Signal Processing At The Department Of Electronics Electrical Communication Engineering Department, Iit

Volltext

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

Volltext

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

Volltext

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

Volltext

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

Volltext

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

Volltext

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

Volltext

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

Volltext

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

“… In practical applications, such as singing voice synthesis, there is a demand for neural vocoders to generate high-fidelity speech waveforms with flexible pitch control …”
Volltext

A Large-Scale Evaluation of Speech Foundation Models von 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

Volltext

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

“… This study extends the application of predicted MOS to the task of Fake Audio Detection (FAD) as we expect that MOS can be used to assess how close synthesized speech is to the natural human voice …”
Volltext

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

Volltext

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

“… We present a novel controllable system for generating single stems to accompany musical mixes of arbitrary length …”
Volltext

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

Volltext

Data Driven Grapheme-to-Phoneme Representations for a Lexicon-Free Text-to-Speech von 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 …”
Volltext

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

Volltext

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

Volltext

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

Volltext

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

“… The exterior radiation from the loudspeakers in sound field synthesis systems can be problematic in practical situations …”
Volltext

Cross-Corpus Multilingual Speech Emotion Recognition: Amharic vs. Other Languages von Ephrem Afele Retta, Richard Sutcliffe, Jabar Mahmood, Michael Abebe Berwo, Eiad Almekhlafi, Sajjad Ahmad Khan, Shehzad Ashraf Chaudhry, Mustafa Mhamed, Jun Feng

Volltext