English
Related papers

Related papers: Optimization Techniques for a Physical Model of Hu…

200 papers

This paper investigates a method for simulating natural conversation in the model training of end-to-end neural diarization (EEND). Due to the lack of any annotated real conversational dataset, EEND is usually pretrained on a large-scale…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-26 Natsuo Yamashita , Shota Horiguchi , Takeshi Homma

During the pre-training step of natural language models, the main objective is to learn a general representation of the pre-training dataset, usually requiring large amounts of textual data to capture the complexity and diversity of natural…

Computation and Language · Computer Science 2023-10-23 Tobias Deußer , Cong Zhao , Wolfgang Krämer , David Leonhard , Christian Bauckhage , Rafet Sifa

Randomized experiments are the gold standard for evaluating the effects of changes to real-world systems. Data in these tests may be difficult to collect and outcomes may have high variance, resulting in potentially large measurement error.…

Machine Learning · Statistics 2018-06-27 Benjamin Letham , Brian Karrer , Guilherme Ottoni , Eytan Bakshy

We present the first neural target speech extraction (TSE) system that uses human feedback for iterative refinement. Our approach allows users to mark specific segments of the TSE output, generating an edit mask. The refinement system then…

Sound · Computer Science 2025-08-06 Malek Itani , Ashton Graves , Sefik Emre Eskimez , Shyamnath Gollakota

In this paper we address speaker-independent multichannel speech enhancement in unknown noisy environments. Our work is based on a well-established multichannel local Gaussian modeling framework. We propose to use a neural network for…

Sound · Computer Science 2019-05-01 Simon Leglaive , Laurent Girin , Radu Horaud

We present a training method with linguistic speech regularization that improves the robustness of spontaneous speech synthesis methods with filled pause (FP) insertion. Spontaneous speech synthesis is aimed at producing speech with…

Sound · Computer Science 2023-09-20 Yuta Matsunaga , Takaaki Saeki , Shinnosuke Takamichi , Hiroshi Saruwatari

The intelligibility of speech severely degrades in the presence of environmental noise and reverberation. In this paper, we propose a novel deep learning based system for modifying the speech signal to increase its intelligibility under the…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-17 Haoyu Li , Junichi Yamagishi

Objective evaluation of audio processed with Time-Scale Modification (TSM) remains an open problem. Recently, a dataset of time-scaled audio with subjective quality labels was published and used to create an initial objective measure of…

Audio and Speech Processing · Electrical Eng. & Systems 2021-04-07 Timothy Roberts , Kuldip K. Paliwal

Current speech production systems predominantly rely on large transformer models that operate as black boxes, providing little interpretability or grounding in the physical mechanisms of human speech. We address this limitation by proposing…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-08 Akshay Anand , Chenxu Guo , Cheol Jun Cho , Jiachen Lian , Gopala Anumanchipalli

Various applications of voice synthesis have been developed independently despite the fact that they generate "voice" as output in common. In addition, most of the voice synthesis models still require a large number of audio data paired…

Sound · Computer Science 2022-11-18 Hyeong-Seok Choi , Jinhyeok Yang , Juheon Lee , Hyeongju Kim

Recent advancements in speech synthesis have enabled large language model (LLM)-based systems to perform zero-shot generation with controllable content, timbre, speaker identity, and emotion through input prompts. As a result, these models…

Singing voice synthesis has made remarkable progress in generating natural and high-quality voices. However, existing methods rarely provide precise control over vocal techniques such as intensity, mixed voice, falsetto, bubble, and breathy…

Sound · Computer Science 2025-04-22 Wenxiang Guo , Yu Zhang , Changhao Pan , Rongjie Huang , Li Tang , Ruiqi Li , Zhiqing Hong , Yongqi Wang , Zhou Zhao

By representing speaker characteristic as a single fixed-length vector extracted solely from speech, we can train a neural multi-speaker speech synthesis model by conditioning the model on those vectors. This model can also be adapted to…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-09 Hieu-Thi Luong , Junichi Yamagishi

Sound field reproduction methods based on numerical optimization, which aim to minimize the error between synthesized and desired sound fields, are useful in many practical scenarios because of their flexibility in the array geometry of…

Audio and Speech Processing · Electrical Eng. & Systems 2021-11-23 Shoichi Koyama , Keisuke Kimura , Natsuki Ueno

Although large-scale self-supervised learning (SSL) models like WavLM have achieved state-of-the-art performance in speech processing, their significant size impedes deployment on resource-constrained devices. While structured pruning is a…

Audio and Speech Processing · Electrical Eng. & Systems 2025-11-11 Junyi Peng , Lin Zhang , Jiangyu Han , Oldřich Plchot , Johan Rohdin , Themos Stafylakis , Shuai Wang , Jan Černocký

In the articulatory synthesis task, speech is synthesized from input features containing information about the physical behavior of the human vocal tract. This task provides a promising direction for speech synthesis research, as the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-09-15 Peter Wu , Shinji Watanabe , Louis Goldstein , Alan W Black , Gopala K. Anumanchipalli

Personalized speech enhancement (PSE) models utilize additional cues, such as speaker embeddings like d-vectors, to remove background noise and interfering speech in real-time and thus improve the speech quality of online video conferencing…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-20 Sefik Emre Eskimez , Takuya Yoshioka , Huaming Wang , Xiaofei Wang , Zhuo Chen , Xuedong Huang

This paper tackles the scarcity of benchmarking data in disentangled auditory representation learning. We introduce SynTone, a synthetic dataset with explicit ground truth explanatory factors for evaluating disentanglement techniques.…

Sound · Computer Science 2024-02-19 Yusuf Brima , Ulf Krumnack , Simone Pika , Gunther Heidemann

Supervised speech enhancement relies on parallel databases of degraded speech signals and their clean reference signals during training. This setting prohibits the use of real-world degraded speech data that may better represent the…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-22 Yangyang Xia , Buye Xu , Anurag Kumar

We propose a novel approach to significantly improve the intelligibility in the Non-Audible Murmur (NAM)-to-speech conversion task, leveraging self-supervision and sequence-to-sequence (Seq2Seq) learning techniques. Unlike conventional…

Sound · Computer Science 2024-07-29 Neil Shah , Shirish Karande , Vineet Gandhi