most citedLess is More: Accurate Speech Recognition & Translation without Web-Scale Data

1 citations · 1 across the 6 of their papers we have counts for

collaborators

9 papers

cs.CL2024

BESTOW: Efficient and Streamable Speech Language Model with the Best of Two Worlds in GPT and T5

Zhehuai Chen, He Huang, Oleksii Hrinchuk +5

Incorporating speech understanding capabilities into pretrained large-language models has become a vital research direction (SpeechLLM). The previous architectures can be categoriz…

cs.CL20241 cited

Less is More: Accurate Speech Recognition & Translation without Web-Scale Data

Krishna C. Puvvada, Piotr Żelasko, He Huang +9

Recent advances in speech recognition and translation rely on hundreds of thousands of hours of Internet speech data. We argue that state-of-the art accuracy can be reached without…

eess.AS2024

DeSTA: Enhancing Speech Language Models through Descriptive Speech-Text Alignment

Ke-Han Lu, Zhehuai Chen, Szu-Wei Fu +4

Recent speech language models (SLMs) typically incorporate pre-trained speech models to extend the capabilities from large language models (LLMs). In this paper, we propose a Descr…

eess.AS2024

Instruction Data Generation and Unsupervised Adaptation for Speech Language Models

Vahid Noroozi, Zhehuai Chen, Somshubra Majumdar +3

In this paper, we propose three methods for generating synthetic samples to train and evaluate multimodal large language models capable of processing both text and speech inputs. A…

cs.CL2024

Transducers with Pronunciation-aware Embeddings for Automatic Speech Recognition

Hainan Xu, Zhehuai Chen, Fei Jia +1

This paper proposes Transducers with Pronunciation-aware Embeddings (PET). Unlike conventional Transducers where the decoder embeddings for different tokens are trained independent…

cs.CL2024

High-precision Voice Search Query Correction via Retrievable Speech-text Embedings

Christopher Li, Gary Wang, Kyle Kastner +9

Automatic speech recognition (ASR) systems can suffer from poor recall for various reasons, such as noisy audio, lack of sufficient training data, etc. Previous work has shown that…