261 citations · 439 across the 15 of their papers we have counts for
15 papers
Low-rank Adaptation Method for Wav2vec2-based Fake Audio Detection
Chenglong Wang, Jiangyan Yi, Xiaohui Zhang +3
Self-supervised speech models are a rapidly developing research topic in fake audio detection. Many pre-trained models can serve as feature extractors, learning richer and higher-l…
Anchored Speech Recognition with Neural Transducers
Desh Raj, Junteng Jia, Jay Mahadeokar +4
Neural transducers have achieved human level performance on standard speech recognition benchmarks. However, their performance significantly degrades in the presence of cross-talk,…
Towards Measuring Fairness in Speech Recognition: Casual Conversations Dataset Transcriptions
Chunxi Liu, Michael Picheny, Leda Sarı +7
It is well known that many machine learning systems demonstrate bias towards specific groups of individuals. This problem has been studied extensively in the Facial Recognition are…
Accent-Robust Automatic Speech Recognition Using Supervised and Unsupervised Wav2vec Embeddings
Jialu Li, Vimal Manohar, Pooja Chitkara +5
Speech recognition models often obtain degraded performance when tested on speech with unseen accents. Domain-adversarial training (DAT) and multi-task learning (MTL) are two commo…
Streaming Transformer Transducer Based Speech Recognition Using Non-Causal Convolution
Yangyang Shi, Chunyang Wu, Dilin Wang +9
This paper improves the streaming transformer transducer for speech recognition by using non-causal convolution. Many works apply the causal convolution to improve streaming transf…
Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernet
Haichuan Yang, Yuan Shangguan, Dilin Wang +6
From wearables to powerful smart devices, modern automatic speech recognition (ASR) models run on a variety of edge devices with different computational budgets. To navigate the Pa…
On lattice-free boosted MMI training of HMM and CTC-based full-context ASR models
Xiaohui Zhang, Vimal Manohar, David Zhang +7
Hybrid automatic speech recognition (ASR) models are typically sequentially trained with CTC or LF-MMI criteria. However, they have vastly different legacies and are usually implem…
Benchmarking LF-MMI, CTC and RNN-T Criteria for Streaming ASR
Xiaohui Zhang, Frank Zhang, Chunxi Liu +8
In this work, to measure the accuracy and efficiency for a latency-controlled streaming automatic speech recognition (ASR) application, we perform comprehensive evaluations on thre…
Faster, Simpler and More Accurate Hybrid ASR Systems Using Wordpieces
Frank Zhang, Yongqiang Wang, Xiaohui Zhang +3
In this work, we first show that on the widely used LibriSpeech benchmark, our transformer-based context-dependent connectionist temporal classification (CTC) system produces state…
From Senones to Chenones: Tied Context-Dependent Graphemes for Hybrid Speech Recognition
Duc Le, Xiaohui Zhang, Weiyi Zheng +3
There is an implicit assumption that traditional hybrid approaches for automatic speech recognition (ASR) cannot directly model graphemes and need to rely on phonetic lexicons to g…
Deja-vu: Double Feature Presentation and Iterated Loss in Deep Transformer Networks
Andros Tjandra, Chunxi Liu, Frank Zhang +5
Deep acoustic models typically receive features in the first layer of the network, and process increasingly abstract representations in the subsequent layers. Here, we propose to f…
Transformer-based Acoustic Modeling for Hybrid Speech Recognition
Yongqiang Wang, Abdelrahman Mohamed, Duc Le +10
We propose and evaluate transformer-based acoustic models (AMs) for hybrid speech recognition. Several modeling choices are discussed in this work, including various positional emb…
Multilingual Graphemic Hybrid ASR with Massive Data Augmentation
Chunxi Liu, Qiaochu Zhang, Xiaohui Zhang +3
Towards developing high-performing ASR for low-resource languages, approaches to address the lack of resources are to make use of data from multiple languages, and to augment the t…
Acoustic data-driven lexicon learning based on a greedy pronunciation selection framework
Xiaohui Zhang, Vimal Manohar, Daniel Povey +1
Speech recognition systems for irregularly-spelled languages like English normally require hand-written pronunciations. In this paper, we describe a system for automatically obtain…
Parallel training of DNNs with Natural Gradient and Parameter Averaging
Daniel Povey, Xiaohui Zhang, Sanjeev Khudanpur
We describe the neural-network training framework used in the Kaldi speech recognition toolkit, which is geared towards training DNNs with large amounts of training data using mult…