40 citations · 53 across the 10 of their papers we have counts for
10 papers
Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training
Zili Wang, Zhaopeng Qiu, Yuekai Zhang +2
Speculative decoding accelerates rollout generation, which dominates the cost of reinforcement learning (RL) post-training. Online co-training can further increase the draft's accu…
PINNsAgent: Automated PDE Surrogation with Large Language Models
Qingpo Wuwu, Chonghan Gao, Tianyu Chen +6
Solving partial differential equations (PDEs) using neural methods has been a long-standing scientific and engineering research pursuit. Physics-Informed Neural Networks (PINNs) ha…
TouchTTS: An Embarrassingly Simple TTS Framework that Everyone Can Touch
Xingchen Song, Mengtao Xing, Changwei Ma +9
It is well known that LLM-based systems are data-hungry. Recent LLM-based TTS works typically employ complex data processing pipelines to obtain high-quality training data. These s…
TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch
Jeff Hwang, Moto Hira, Caroline Chen +21
TorchAudio is an open-source audio and speech processing library built for PyTorch. It aims to accelerate the research and development of audio and speech technologies by providing…
TrimTail: Low-Latency Streaming ASR with Simple but Effective Spectrogram-Level Length Penalty
Xingchen Song, Di Wu, Zhiyong Wu +6
In this paper, we present TrimTail, a simple but effective emission regularization method to improve the latency of streaming ASR models. The core idea of TrimTail is to apply leng…
ESPnet-SLU: Advancing Spoken Language Understanding through ESPnet
Siddhant Arora, Siddharth Dalmia, Pavel Denisov +10
As Automatic Speech Processing (ASR) systems are getting better, there is an increasing interest of using the ASR output to do downstream Natural Language Processing (NLP) tasks. H…
SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognition
Patrick K. O'Neill, Vitaly Lavrukhin, Somshubra Majumdar +10
In the English speech-to-text (STT) machine learning task, acoustic models are conventionally trained on uncased Latin characters, and any necessary orthography (such as capitaliza…
Tiny Transducer: A Highly-efficient Speech Recognition Model on Edge Devices
Yuekai Zhang, Sining Sun, Long Ma
This paper proposes an extremely lightweight phone-based transducer model with a tiny decoding graph on edge devices. First, a phone synchronous decoding (PSD) algorithm based on b…
Recent Developments on ESPnet Toolkit Boosted by Conformer
Pengcheng Guo, Florian Boyer, Xuankai Chang +12
In this study, we present recent developments on ESPnet: End-to-End Speech Processing toolkit, which mainly involves a recently proposed architecture called Conformer, Convolution-…
Sequence-to-sequence Singing Voice Synthesis with Perceptual Entropy Loss
Jiatong Shi, Shuai Guo, Nan Huo +2
The neural network (NN) based singing voice synthesis (SVS) systems require sufficient data to train well and are prone to over-fitting due to data scarcity. However, we often enco…