15 citations · 60 across the 22 of their papers we have counts for
23 papers
Binary and Ternary Natural Language Generation
Zechun Liu, Barlas Oguz, Aasish Pappu +2
Ternary and binary neural networks enable multiplication-free computation and promise multiple orders of magnitude efficiency gains over full-precision networks if implemented on s…
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
Zechun Liu, Barlas Oguz, Changsheng Zhao +6
Several post-training quantization methods have been applied to large language models (LLMs), and have been shown to perform well down to 8-bits. We find that these methods break d…
Multi-Head State Space Model for Speech Recognition
Yassir Fathullah, Chunyang Wu, Yuan Shangguan +8
State space models (SSMs) have recently shown promising results on small-scale sequence and language modelling tasks, rivalling and outperforming many attention-based approaches. I…
Improving Fast-slow Encoder based Transducer with Streaming Deliberation
Ke Li, Jay Mahadeokar, Jinxi Guo +5
This paper introduces a fast-slow encoder based transducer with streaming deliberation for end-to-end automatic speech recognition. We aim to improve the recognition accuracy of th…
LiCo-Net: Linearized Convolution Network for Hardware-efficient Keyword Spotting
Haichuan Yang, Zhaojun Yang, Li Wan +10
This paper proposes a hardware-efficient architecture, Linearized Convolution Network (LiCo-Net) for keyword spotting. It is optimized specifically for low-power processor units li…
Biased Self-supervised learning for ASR
Florian L. Kreyssig, Yangyang Shi, Jinxi Guo +3
Self-supervised learning via masked prediction pre-training (MPPT) has shown impressive performance on a range of speech-processing tasks. This paper proposes a method to bias self…
SCA: Streaming Cross-attention Alignment for Echo Cancellation
Yang Liu, Yangyang Shi, Yun Li +3
End-to-End deep learning has shown promising results for speech enhancement tasks, such as noise suppression, dereverberation, and speech separation. However, most state-of-the-art…
Learning a Dual-Mode Speech Recognition Model via Self-Pruning
Chunxi Liu, Yuan Shangguan, Haichuan Yang +3
There is growing interest in unifying the streaming and full-context automatic speech recognition (ASR) networks into a single end-to-end ASR model to simplify the model training a…
Streaming parallel transducer beam search with fast-slow cascaded encoders
Jay Mahadeokar, Yangyang Shi, Ke Li +5
Streaming ASR with strict latency constraints is required in many speech recognition applications. In order to achieve the required latency, streaming ASR models sacrifice accuracy…
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…
Transferring Voice Knowledge for Acoustic Event Detection: An Empirical Study
Dawei Liang, Yangyang Shi, Yun Wang +6
Detection of common events and scenes from audio is useful for extracting and understanding human contexts in daily life. Prior studies have shown that leveraging knowledge from a…
TorchAudio: Building Blocks for Audio and Speech Processing
Yao-Yuan Yang, Moto Hira, Zhaoheng Ni +20
This document describes version 0.10 of TorchAudio: building blocks for machine learning applications in the audio and speech processing domain. The objective of TorchAudio is to a…
Collaborative Training of Acoustic Encoders for Speech Recognition
Varun Nagaraja, Yangyang Shi, Ganesh Venkatesh +3
On-device speech recognition requires training models of different sizes for deploying on devices with various computational budgets. When building such different models, we can be…
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…
Flexi-Transducer: Optimizing Latency, Accuracy and Compute forMulti-Domain On-Device Scenarios
Jay Mahadeokar, Yangyang Shi, Yuan Shangguan +7
Often, the storage and computational constraints of embeddeddevices demand that a single on-device ASR model serve multiple use-cases / domains. In this paper, we propose aFlexible…
Dynamic Encoder Transducer: A Flexible Solution For Trading Off Accuracy For Latency
Yangyang Shi, Varun Nagaraja, Chunyang Wu +9
We propose a dynamic encoder transducer (DET) for on-device speech recognition. One DET model scales to multiple devices with different computation capacities without retraining or…
Dissecting User-Perceived Latency of On-Device E2E Speech Recognition
Yuan Shangguan, Rohit Prabhavalkar, Hang Su +8
As speech-enabled devices such as smartphones and smart speakers become increasingly ubiquitous, there is growing interest in building automatic speech recognition (ASR) systems th…
Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion
Duc Le, Mahaveer Jain, Gil Keren +9
How to leverage dynamic contextual information in end-to-end speech recognition has remained an active research area. Previous solutions to this problem were either designed for sp…
Streaming Attention-Based Models with Augmented Memory for End-to-End Speech Recognition
Ching-Feng Yeh, Yongqiang Wang, Yangyang Shi +4
Attention-based models have been gaining popularity recently for their strong performance demonstrated in fields such as machine translation and automatic speech recognition. One m…
Transformer in action: a comparative study of transformer-based acoustic models for large scale speech recognition applications
Yongqiang Wang, Yangyang Shi, Frank Zhang +4
In this paper, we summarize the application of transformer and its streamable variant, Emformer based acoustic model for large scale speech recognition applications. We compare the…
Emformer: Efficient Memory Transformer Based Acoustic Model For Low Latency Streaming Speech Recognition
Yangyang Shi, Yongqiang Wang, Chunyang Wu +5
This paper proposes an efficient memory transformer Emformer for low latency streaming speech recognition. In Emformer, the long-range history context is distilled into an augmente…
Weak-Attention Suppression For Transformer Based Speech Recognition
Yangyang Shi, Yongqiang Wang, Chunyang Wu +5
Transformers, originally proposed for natural language processing (NLP) tasks, have recently achieved great success in automatic speech recognition (ASR). However, adjacent acousti…
Streaming Transformer-based Acoustic Models Using Self-attention with Augmented Memory
Chunyang Wu, Yongqiang Wang, Yangyang Shi +2
Transformer-based acoustic modeling has achieved great suc-cess for both hybrid and sequence-to-sequence speech recogni-tion. However, it requires access to the full sequence, and…