Search Results for author: Siqi Zheng

Found 23 papers, 9 papers with code

Loss Masking Is Not Needed in Decoder-only Transformer for Discrete-token Based ASR

no code implementations8 Nov 2023 Qian Chen, Wen Wang, Qinglin Zhang, Siqi Zheng, Shiliang Zhang, Chong Deng, Yukun Ma, Hai Yu, Jiaqing Liu, Chong Zhang

Specifically, all these models utilize Loss Masking on the input speech tokens for the ASR task, which means that these models do not explicitly model the dependency between the speech tokens.

FunCodec: A Fundamental, Reproducible and Integrable Open-source Toolkit for Neural Speech Codec

1 code implementation14 Sep 2023 Zhihao Du, Shiliang Zhang, Kai Hu, Siqi Zheng

We also demonstrate that the pre-trained models are suitable for downstream tasks, including automatic speech recognition and personalized text-to-speech synthesis.

Automatic Speech Recognition speech-recognition +3

Self-Distillation Network with Ensemble Prototypes: Learning Robust Speaker Representations without Supervision

1 code implementation5 Aug 2023 Yafeng Chen, Siqi Zheng, Hui Wang, Luyao Cheng, Qian Chen, Shiliang Zhang

It assigns representation of augmented views of utterances to the same prototypes as the representation of the original view, thereby enabling effective knowledge transfer between the views.

Representation Learning Speaker Verification +1

Improving BERT with Hybrid Pooling Network and Drop Mask

no code implementations14 Jul 2023 Qian Chen, Wen Wang, Qinglin Zhang, Chong Deng, Ma Yukun, Siqi Zheng

Transformer-based pre-trained language models, such as BERT, achieve great success in various natural language understanding tasks.

Language Modelling Masked Language Modeling +2

Exploring Speaker-Related Information in Spoken Language Understanding for Better Speaker Diarization

no code implementations22 May 2023 Luyao Cheng, Siqi Zheng, Zhang Qinglin, Hui Wang, Yafeng Chen, Qian Chen

In this paper, we propose methods to extract speaker-related information from semantic content in multi-party meetings, which, as we will show, can further benefit speaker diarization.

speaker-diarization Speaker Diarization +1

An Enhanced Res2Net with Local and Global Feature Fusion for Speaker Verification

2 code implementations22 May 2023 Yafeng Chen, Siqi Zheng, Hui Wang, Luyao Cheng, Qian Chen, Jiajun Qi

This paper proposes a novel architecture called Enhanced Res2Net (ERes2Net), which incorporates both local and global feature fusion techniques to improve the performance.

Speaker Verification

Ditto: A Simple and Efficient Approach to Improve Sentence Embeddings

1 code implementation18 May 2023 Qian Chen, Wen Wang, Qinglin Zhang, Siqi Zheng, Chong Deng, Hai Yu, Jiaqing Liu, Yukun Ma, Chong Zhang

Prior studies diagnose the anisotropy problem in sentence representations from pre-trained language models, e. g., BERT, without fine-tuning.

Language Modelling Semantic Textual Similarity +3

DopplerBAS: Binaural Audio Synthesis Addressing Doppler Effect

no code implementations14 Dec 2022 Jinglin Liu, Zhenhui Ye, Qian Chen, Siqi Zheng, Wen Wang, Qinglin Zhang, Zhou Zhao

Recently, binaural audio synthesis (BAS) has emerged as a promising research field for its applications in augmented and virtual realities.

Contextual Expressive Text-to-Speech

no code implementations26 Nov 2022 Jianhong Tu, Zeyu Cui, Xiaohuan Zhou, Siqi Zheng, Kai Hu, Ju Fan, Chang Zhou

To achieve this task, we construct a synthetic dataset and develop an effective framework.

Speech Synthesis

Pushing the limits of self-supervised speaker verification using regularized distillation framework

1 code implementation8 Nov 2022 Yafeng Chen, Siqi Zheng, Hui Wang, Luyao Cheng, Qian Chen

A range of experiments conducted on the VoxCeleb datasets demonstrate the superiority of the regularized DINO framework in speaker verification.

Data Augmentation Self-Supervised Learning +1

Deep Representation Decomposition for Rate-Invariant Speaker Verification

no code implementations28 May 2022 Fuchuan Tong, Siqi Zheng, Haodong Zhou, Xingjia Xie, Qingyang Hong, Lin Li

While promising performance for speaker verification has been achieved by deep speaker embeddings, the advantage would reduce in the case of speaking-style variability.

Speaker Verification

Speaker Embedding-aware Neural Diarization: an Efficient Framework for Overlapping Speech Diarization in Meeting Scenarios

1 code implementation18 Mar 2022 Zhihao Du, Shiliang Zhang, Siqi Zheng, Zhijie Yan

Through this formulation, we propose the speaker embedding-aware neural diarization (SEND) framework, where a speech encoder, a speaker encoder, two similarity scorers, and a post-processing network are jointly optimized to predict the encoded labels according to the similarities between speech features and speaker embeddings.

Action Detection Activity Detection +2

Speaker Embedding-aware Neural Diarization for Flexible Number of Speakers with Textual Information

2 code implementations28 Nov 2021 Zhihao Du, Shiliang Zhang, Siqi Zheng, Weilong Huang, Ming Lei

In this paper, we reformulate this task as a single-label prediction problem by encoding the multi-speaker labels with power set.

Action Detection Activity Detection +2

BeamTransformer: Microphone Array-based Overlapping Speech Detection

no code implementations9 Sep 2021 Siqi Zheng, Shiliang Zhang, Weilong Huang, Qian Chen, Hongbin Suo, Ming Lei, Jinwei Feng, Zhijie Yan

We propose BeamTransformer, an efficient architecture to leverage beamformer's edge in spatial filtering and transformer's capability in context sequence modeling.

A Real-time Speaker Diarization System Based on Spatial Spectrum

no code implementations20 Jul 2021 Siqi Zheng, Weilong Huang, Xianliang Wang, Hongbin Suo, Jinwei Feng, Zhijie Yan

In this paper we describe a speaker diarization system that enables localization and identification of all speakers present in a conversation or meeting.

speaker-diarization Speaker Diarization +1

Estimating air quality co-benefits of energy transition using machine learning

no code implementations29 May 2021 Da Zhang, Qingyi Wang, Shaojie Song, Simiao Chen, MingWei Li, Lu Shen, Siqi Zheng, Bofeng Cai, Shenhao Wang

Applications of the framework with Chinese data reveal highly heterogeneous health benefits of reducing fossil fuel use in different sectors and regions in China with a mean of \$34/tCO2 and a standard deviation of \$84/tCO2.

BIG-bench Machine Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.