AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline [PDF]
Oriental COCOSDA International Conference on Speech Database and Assessments, 2017 An open-source Mandarin speech corpus called AISHELL-1 is released. It is by far the largest corpus which is suitable for conducting the speech recognition research and building speech recognition systems for Mandarin.
Bu, Hui +4 more
core +2 more sources
Prompting Large Language Models with Speech Recognition Abilities [PDF]
IEEE International Conference on Acoustics, Speech, and Signal Processing, 2023 Large language models (LLMs) have proven themselves highly flexible, able to solve a wide range of generative tasks, such as abstractive summarization and open-ended question answering.
Yassir Fathullah +11 more
semanticscholar +1 more source
Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages [PDF]
arXiv.org, 2023 We introduce the Universal Speech Model (USM), a single large model that performs automatic speech recognition (ASR) across 100+ languages. This is achieved by pre-training the encoder of the model on a large unlabeled multilingual dataset of 12 million (
Yu Zhang +26 more
semanticscholar +1 more source
End-to-End Speech Recognition: A Survey [PDF]
IEEE/ACM Transactions on Audio Speech and Language Processing, 2023 In the last decade of automatic speech recognition (ASR) research, the introduction of deep learning has brought considerable reductions in word error rate of more than 50% relative, compared to modeling without deep learning.
Rohit Prabhavalkar +4 more
semanticscholar +1 more source
Fast Conformer With Linearly Scalable Attention For Efficient Speech Recognition [PDF]
Automatic Speech Recognition & Understanding, 2023 Conformer-based models have become the dominant end-to-end architecture for speech processing tasks. With the objective of enhancing the conformer architecture for efficient training and inference, we carefully redesigned Conformer with a novel ...
D. Rekesh +7 more
semanticscholar +1 more source
SALM: Speech-Augmented Language Model with in-Context Learning for Speech Recognition and Translation [PDF]
IEEE International Conference on Acoustics, Speech, and Signal Processing, 2023 We present a novel Speech Augmented Language Model (SALM) with multitask and in-context learning capabilities. SALM comprises a frozen text LLM, a audio encoder, a modality adapter module, and LoRA layers to accommodate speech input and associated task ...
Zhehuai Chen +8 more
semanticscholar +1 more source
VoxtLM: Unified Decoder-Only Models for Consolidating Speech Recognition, Synthesis and Speech, Text Continuation Tasks [PDF]
IEEE International Conference on Acoustics, Speech, and Signal Processing, 2023 We propose a decoder-only language model, VoxtLM, that can perform four tasks: speech recognition, speech synthesis, text generation, and speech continuation.
Soumi Maiti +5 more
semanticscholar +1 more source
Conformer: Convolution-augmented Transformer for Speech Recognition [PDF]
Interspeech, 2020 Recently Transformer and Convolution neural network (CNN) based models have shown promising results in Automatic Speech Recognition (ASR), outperforming Recurrent neural networks (RNNs).
Anmol Gulati +10 more
semanticscholar +1 more source
End-To-End Audio-Visual Speech Recognition with Conformers [PDF]
IEEE International Conference on Acoustics, Speech, and Signal Processing, 2021 In this work, we present a hybrid CTC/Attention model based on a ResNet-18 and Convolution-augmented transformer (Conformer), that can be trained in an end-to-end manner.
Pingchuan Ma +2 more
semanticscholar +1 more source
Deep Learning Enabled Semantic Communications With Speech Recognition and Synthesis [PDF]
IEEE Transactions on Wireless Communications, 2022 In this paper, we develop a deep learning based semantic communication system for speech transmission, named DeepSC-ST. We take the speech recognition and speech synthesis as the transmission tasks of the communication system, respectively.
Zhenzi Weng +5 more
semanticscholar +1 more source