Fangyuan Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Fangyuan Wang has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Bo Xu
Institute of Automation, Chinese Academy of Sciences, Beijing, China
4 shared publications - Bo Xu
Institute of Automation Chinese Academy of Sciences Beijing China
1 shared publication - Bo Xu
Faculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu, China
1 shared publication - Guanhua Tian
Institute of Automation Chinese Academy of Sciences 100190 Beijing P.R. China
1 shared publication - Heping Li
National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
1 shared publication - Hong-Wei Hao
Institute of Automation Chinese Academy of Sciences 100190 Beijing P.R. China
1 shared publication
Latest Publications
- 10 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 31 (10709908) , 421-425
SSCFormer: Push the Limit of Chunk-Wise Conformer for Streaming ASR Using Sequentially Sampled Chunks and Chunked Causal Convolution
Currently, the chunk-wise schemes are often used to make Automatic Speech Recognition (ASR) models to support streaming deployment. However, existing approaches are unable to capture the global context, lack support for parallel training, or exhibit quadratic complexity for the computation of multi-head self-attention (MHSA). On the other side, the causal convolution, no future context used, has become the de facto module in streaming Conformer. In this letter, we propose SSCFormer to push the limit of chunk-wise Conformer for streaming ASR using the following two techniques: 1) A novel cross-chunks context generation method, named Sequential Sampling Chunk (SSC) scheme, to re-partition chunks from regular partitioned chunks to facilitate efficient long-term contextual interaction within local chunks. 2)The Chunked Causal Convolution (C2Conv) is designed to concurrently capture the left context and chunk-wise future context. Evaluations on AISHELL-1 show that an End-to-End (E2E) CER 5.33% can achieve, which even outperforms a strong time-restricted baseline U2. Moreover, the chunk-wise MHSA computation in our model enables it to train with a large batch size and perform inference with linear complexity.
- 10 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 31 (10709908) , 421-425
SSCFormer: Push the Limit of Chunk-Wise Conformer for Streaming ASR Using Sequentially Sampled Chunks and Chunked Causal Convolution
Currently, the chunk-wise schemes are often used to make Automatic Speech Recognition (ASR) models to support streaming deployment. However, existing approaches are unable to capture the global context, lack support for parallel training, or exhibit quadratic complexity for the computation of multi-head self-attention (MHSA). On the other side, the causal convolution, no future context used, has become the de facto module in streaming Conformer. In this letter, we propose SSCFormer to push the limit of chunk-wise Conformer for streaming ASR using the following two techniques: 1) A novel cross-chunks context generation method, named Sequential Sampling Chunk (SSC) scheme, to re-partition chunks from regular partitioned chunks to facilitate efficient long-term contextual interaction within local chunks. 2)The Chunked Causal Convolution (C2Conv) is designed to concurrently capture the left context and chunk-wise future context. Evaluations on AISHELL-1 show that an End-to-End (E2E) CER 5.33% can achieve, which even outperforms a strong time-restricted baseline U2. Moreover, the chunk-wise MHSA computation in our model enables it to train with a large batch size and perform inference with linear complexity.
- 13 November 2023
- Published by Springer Nature
- p. 174-185
Lead ASR Models to Generalize Better Using Approximated Bias-Variance Tradeoff
- 13 November 2023
- Published by Springer Nature
- p. 174-185
Lead ASR Models to Generalize Better Using Approximated Bias-Variance Tradeoff
- Open Access
P-vectors: A Parallel-Coupled TDNN/Transformer Network for Speaker Verification
Typically, the Time-Delay Neural Network (TDNN) and Transformer can serve as a backbone for Speaker Verification (SV). Both of them have advantages and disadvantages from the perspective of global and local feature modeling. How to effectively integrate these two style features is still an open issue. In this paper, we explore a Parallel-coupled TDNN/Transformer Network (p-vectors) to replace the serial hybrid networks. The p-vectors allows TDNN and Transformer to learn the complementary information from each other through Soft Feature Alignment Interaction (SFAI) under the premise of preserving local and global features. Also, p-vectors uses the Spatial Frequency-channel Attention (SFA) to enhance the spatial interdependence modeling for input features. Finally, the outputs of dual branches of p-vectors are combined by Embedding Aggregation Layer (EAL). Experiments show that p-vectors outperforms MACCIF-TDNN and MFA-Conformer with relative improvements of 11.5% and 13.9% in EER on VoxCeleb1-O.
Open AccessP-vectors: A Parallel-Coupled TDNN/Transformer Network for Speaker Verification
Typically, the Time-Delay Neural Network (TDNN) and Transformer can serve as a backbone for Speaker Verification (SV). Both of them have advantages and disadvantages from the perspective of global and local feature modeling. How to effectively integrate these two style features is still an open issue. In this paper, we explore a Parallel-coupled TDNN/Transformer Network (p-vectors) to replace the serial hybrid networks. The p-vectors allows TDNN and Transformer to learn the complementary information from each other through Soft Feature Alignment Interaction (SFAI) under the premise of preserving local and global features. Also, p-vectors uses the Spatial Frequency-channel Attention (SFA) to enhance the spatial interdependence modeling for input features. Finally, the outputs of dual branches of p-vectors are combined by Embedding Aggregation Layer (EAL). Experiments show that p-vectors outperforms MACCIF-TDNN and MFA-Conformer with relative improvements of 11.5% and 13.9% in EER on VoxCeleb1-O.
- 14 April 2023
- Published by Springer Nature
- p. 39-50
Shifted Chunk Encoder for Transformer Based Streaming End-to-End ASR
- 14 April 2023
- Published by Springer Nature
- p. 39-50
Shifted Chunk Encoder for Transformer Based Streaming End-to-End ASR
- Open Access
Shifted Chunk Encoder for Transformer Based Streaming End-to-End ASR
Currently, there are mainly three kinds of Transformer encoder based streaming End to End (E2E) Automatic Speech Recognition (ASR) approaches, namely time-restricted methods, chunk-wise methods, and memory-based methods. Generally, all of them have limitations in aspects of linear computational complexity, global context modeling, and parallel training. In this work, we aim to build a model to take all these three advantages for streaming Transformer ASR. Particularly, we propose a shifted chunk mechanism for the chunk-wise Transformer which provides cross-chunk connections between chunks. Therefore, the global context modeling ability of chunk-wise models can be significantly enhanced while all the original merits inherited. We integrate this scheme with the chunk-wise Transformer and Conformer, and identify them as SChunk-Transformer and SChunk-Conformer, respectively. Experiments on AISHELL-1 show that the SChunk-Transformer and SChunk-Conformer can respectively achieve CER 6.43% and 5.77%. And the linear complexity makes them possible to train with large batches and infer more efficiently. Our models can significantly outperform their conventional chunk-wise counterparts, while being competitive, with only 0.22 absolute CER drop, when compared with U2 which has quadratic complexity. A better CER can be achieved if compared with existing chunk-wise or memory-based methods, such as HS-DACS and MMA. Code is released.
Open AccessShifted Chunk Encoder for Transformer Based Streaming End-to-End ASR
Currently, there are mainly three kinds of Transformer encoder based streaming End to End (E2E) Automatic Speech Recognition (ASR) approaches, namely time-restricted methods, chunk-wise methods, and memory-based methods. Generally, all of them have limitations in aspects of linear computational complexity, global context modeling, and parallel training. In this work, we aim to build a model to take all these three advantages for streaming Transformer ASR. Particularly, we propose a shifted chunk mechanism for the chunk-wise Transformer which provides cross-chunk connections between chunks. Therefore, the global context modeling ability of chunk-wise models can be significantly enhanced while all the original merits inherited. We integrate this scheme with the chunk-wise Transformer and Conformer, and identify them as SChunk-Transformer and SChunk-Conformer, respectively. Experiments on AISHELL-1 show that the SChunk-Transformer and SChunk-Conformer can respectively achieve CER 6.43% and 5.77%. And the linear complexity makes them possible to train with large batches and infer more efficiently. Our models can significantly outperform their conventional chunk-wise counterparts, while being competitive, with only 0.22 absolute CER drop, when compared with U2 which has quadratic complexity. A better CER can be achieved if compared with existing chunk-wise or memory-based methods, such as HS-DACS and MMA. Code is released.
- Open Access
Short Text Hashing Improved by Integrating Multi-Granularity Topics and Tags
Due to computational and storage efficiencies of compact binary codes, hashing has been widely used for large-scale similarity search. Unfortunately, many existing hashing methods based on observed keyword features are not effective for short texts due to the sparseness and shortness. Recently, some researchers try to utilize latent topics of certain granularity to preserve semantic similarity in hash codes beyond keyword matching. However, topics of certain granularity are not adequate to represent the intrinsic semantic information. In this paper, we present a novel unified approach for short text Hashing using Multi-granularity Topics and Tags, dubbed HMTT. In particular, we propose a selection method to choose the optimal multi-granularity topics depending on the type of dataset, and design two distinct hashing strategies to incorporate multi-granularity topics. We also propose a simple and effective method to exploit tags to enhance the similarity of related texts. We carry out extensive experiments on one short text dataset as well as on one normal text dataset. The results demonstrate that our approach is effective and significantly outperforms baselines on several evaluation metrics.
Open AccessShort Text Hashing Improved by Integrating Multi-Granularity Topics and Tags
Due to computational and storage efficiencies of compact binary codes, hashing has been widely used for large-scale similarity search. Unfortunately, many existing hashing methods based on observed keyword features are not effective for short texts due to the sparseness and shortness. Recently, some researchers try to utilize latent topics of certain granularity to preserve semantic similarity in hash codes beyond keyword matching. However, topics of certain granularity are not adequate to represent the intrinsic semantic information. In this paper, we present a novel unified approach for short text Hashing using Multi-granularity Topics and Tags, dubbed HMTT. In particular, we propose a selection method to choose the optimal multi-granularity topics depending on the type of dataset, and design two distinct hashing strategies to incorporate multi-granularity topics. We also propose a simple and effective method to exploit tags to enhance the similarity of related texts. We carry out extensive experiments on one short text dataset as well as on one normal text dataset. The results demonstrate that our approach is effective and significantly outperforms baselines on several evaluation metrics.
- 20 December 2013
- Published by China Science Publishing & Media Ltd. in Journal of Software
- Vol. 24 (12) , 2921-2936
Video Clip Identification Algorithm Based on Spatio-Temporal Ordinal Measures
- 20 December 2013
- Published by China Science Publishing & Media Ltd. in Journal of Software
- Vol. 24 (12) , 2921-2936
Video Clip Identification Algorithm Based on Spatio-Temporal Ordinal Measures