93 citations · 307 across the 35 of their papers we have counts for
35 papers
Ultra Dual-Path Compression For Joint Echo Cancellation And Noise Suppression
Hangting Chen, Jianwei Yu, Yi Luo +4
Echo cancellation and noise reduction are essential for full-duplex communication, yet most existing neural networks have high computational costs and are inflexible in tuning mode…
The Sound Demixing Challenge 2023 $\unicode{x2013}$ Music Demixing Track
Giorgio Fabbro, Stefan Uhlich, Chieh-Hsin Lai +24
This paper summarizes the music demixing (MDX) track of the Sound Demixing Challenge (SDX'23). We provide a summary of the challenge setup and introduce the task of robust music so…
Use of Speech Impairment Severity for Dysarthric Speech Recognition
Mengzhe Geng, Zengrui Jin, Tianzi Wang +7
A key challenge in dysarthric speech recognition is the speaker-level diversity attributed to both speaker-identity associated factors such as gender, and speech impairment severit…
High Fidelity Speech Enhancement with Band-split RNN
Jianwei Yu, Yi Luo, Hangting Chen +2
Despite the rapid progress in speech enhancement (SE) research, enhancing the quality of desired speech in environments with strong noise and interfering speakers remains challengi…
NoreSpeech: Knowledge Distillation based Conditional Diffusion Model for Noise-robust Expressive TTS
Dongchao Yang, Songxiang Liu, Jianwei Yu +3
Expressive text-to-speech (TTS) can synthesize a new speaking style by imiating prosody and timbre from a reference audio, which faces the following challenges: (1) The highly dyna…
Bayes risk CTC: Controllable CTC alignment in Sequence-to-Sequence tasks
Jinchuan Tian, Brian Yan, Jianwei Yu +3
Sequence-to-Sequence (seq2seq) tasks transcribe the input sequence to a target sequence. The Connectionist Temporal Classification (CTC) criterion is widely used in multiple seq2se…
Music Source Separation with Band-split RNN
Yi Luo, Jianwei Yu
The performance of music source separation (MSS) models has been greatly improved in recent years thanks to the development of novel neural network architectures and training pipel…
FRA-RIR: Fast Random Approximation of the Image-source Method
Yi Luo, Jianwei Yu
The training of modern speech processing systems often requires a large amount of simulated room impulse response (RIR) data in order to allow the systems to generalize well in rea…
Diffsound: Discrete Diffusion Model for Text-to-sound Generation
Dongchao Yang, Jianwei Yu, Helin Wang +4
Generating sound effects that humans want is an important topic. However, there are few studies in this area for sound generation. In this study, we investigate generating sound co…
Automatic Prosody Annotation with Pre-Trained Text-Speech Model
Ziqian Dai, Jianwei Yu, Yan Wang +5
Prosodic boundary plays an important role in text-to-speech synthesis (TTS) in terms of naturalness and readability. However, the acquisition of prosodic boundary labels relies on…
LAE: Language-Aware Encoder for Monolingual and Multilingual ASR
Jinchuan Tian, Jianwei Yu, Chunlei Zhang +3
Despite the rapid progress in automatic speech recognition (ASR) research, recognizing multilingual speech using a unified ASR system remains highly challenging. Previous works on…
Audio-visual multi-channel speech separation, dereverberation and recognition
Guinan Li, Jianwei Yu, Jiajun Deng +2
Despite the rapid advance of automatic speech recognition (ASR) technologies, accurate recognition of cocktail party speech characterised by the interference from overlapping speak…
Improving Target Sound Extraction with Timestamp Information
Helin Wang, Dongchao Yang, Chao Weng +2
Target sound extraction (TSE) aims to extract the sound part of a target sound event class from a mixture audio with multiple sound events. The previous works mainly focus on the p…
Integrating Lattice-Free MMI into End-to-End Speech Recognition
Jinchuan Tian, Jianwei Yu, Chao Weng +2
In automatic speech recognition (ASR) research, discriminative criteria have achieved superior performance in DNN-HMM systems. Given this success, the adoption of discriminative cr…
On-the-Fly Feature Based Rapid Speaker Adaptation for Dysarthric and Elderly Speech Recognition
Mengzhe Geng, Xurong Xie, Rongfeng Su +7
Accurate recognition of dysarthric and elderly speech remain challenging tasks to date. Speaker-level heterogeneity attributed to accent or gender, when aggregated with age and spe…
Recent Progress in the CUHK Dysarthric Speech Recognition System
Shansong Liu, Mengzhe Geng, Shoukang Hu +5
Despite the rapid progress of automatic speech recognition (ASR) technologies in the past few decades, recognition of disordered speech remains a highly challenging task to date. D…
Investigation of Data Augmentation Techniques for Disordered Speech Recognition
Mengzhe Geng, Xurong Xie, Shansong Liu +4
Disordered speech recognition is a highly challenging task. The underlying neuro-motor conditions of people with speech disorders, often compounded with co-occurring physical disab…
Spectro-Temporal Deep Features for Disordered Speech Assessment and Recognition
Mengzhe Geng, Shansong Liu, Jianwei Yu +6
Automatic recognition of disordered speech remains a highly challenging task to date. Sources of variability commonly found in normal speech including accent, age or gender, when f…
Improving Mandarin End-to-End Speech Recognition with Word N-gram Language Model
Jinchuan Tian, Jianwei Yu, Chao Weng +2
Despite the rapid progress of end-to-end (E2E) automatic speech recognition (ASR), it has been shown that incorporating external language models (LMs) into the decoding can further…
Consistent Training and Decoding For End-to-end Speech Recognition Using Lattice-free MMI
Jinchuan Tian, Jianwei Yu, Chao Weng +4
Recently, End-to-End (E2E) frameworks have achieved remarkable results on various Automatic Speech Recognition (ASR) tasks. However, Lattice-Free Maximum Mutual Information (LF-MMI…
Mixed Precision of Quantization of Transformer Language Models for Speech Recognition
Junhao Xu, Shoukang Hu, Jianwei Yu +2
State-of-the-art neural language models represented by Transformers are becoming increasingly complex and expensive for practical applications. Low-bit deep neural network quantiza…
Mixed Precision Low-bit Quantization of Neural Network Language Models for Speech Recognition
Junhao Xu, Jianwei Yu, Shoukang Hu +2
State-of-the-art language models (LMs) represented by long-short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming increasingly complex and expensive…
Low-bit Quantization of Recurrent Neural Network Language Models Using Alternating Direction Methods of Multipliers
Junhao Xu, Xie Chen, Shoukang Hu +3
The high memory consumption and computational costs of Recurrent neural network language models (RNNLMs) limit their wider application on resource constrained devices. In recent ye…
Mixed Precision DNN Qunatization for Overlapped Speech Separation and Recognition
Junhao Xu, Jianwei Yu, Xunying Liu +1
Recognition of overlapped speech has been a highly challenging task to date. State-of-the-art multi-channel speech separation system are becoming increasingly complex and expensive…